{ "query": "in 6 sentences what is complex numbers?", "namespace": "cdf5e841-bd92-4996-b7f2-7c2a398184c5", "messages": [ { "role": "assistant", "content": "Hallo diverse NF SepTest! Ich bin Simon, der KI-Chatbot, der das Large Language Model gpt-4o-mini-2024-07-18 verwendet, um Ihre Fragen zu beantworten. Ich freue mich, Ihnen bei Ihren Anliegen zu helfen!\n\nHier sind einige Themen, \u00fcber die wir sprechen k\u00f6nnten: \n\n1. \ud83d\udcd8 Einf\u00fchrung in komplexe Zahlen und ihre Eigenschaften\n2. \ud83d\udd0d Differenzierung komplexer Funktionen und die Cauchy-Riemann-Gleichungen\n3. \ud83d\udcc8 Integration komplexer Funktionen und Cauchys Integralsatz\n4. \ud83e\uddee Taylor- und Laurent-Reihen in der komplexen Analyse\n5. \ud83c\udf10 Isolierte Singularit\u00e4ten und der Residuensatz\n6. \ud83d\udcca Anwendungen der komplexen Analyse in der Mathematik\n7. \ud83d\udcdd \u00dcbungen und L\u00f6sungen zu komplexen Zahlen und Funktionen\n8. \ud83d\udcda Die Bedeutung von harmonischen Funktionen in der komplexen Analyse\n9. \ud83d\udd17 Verbindungen zwischen komplexer und reeller Analyse\n10. \ud83e\udde9 Topologische Konzepte in der komplexen Analyse\n\nGibt es ein bestimmtes Thema auf dieser Liste, das Sie n\u00e4her erkunden m\u00f6chten?" }, { "role": "user", "content": "halo" }, { "role": "assistant", "content": "Hallo! Wie kann ich Ihnen helfen? Gibt es eine spezifische Frage oder ein Thema, \u00fcber das Sie mehr wissen m\u00f6chten?" }, { "role": "user", "content": "what are numbers?" }, { "role": "assistant", "content": "Numbers are abstract concepts used to represent quantities, values, or positions in a sequence. They can be classified into various types, including:\n\n1. **Natural Numbers**: The set of positive integers (1, 2, 3, ...).\n2. **Whole Numbers**: Natural numbers including zero (0, 1, 2, 3, ...).\n3. **Integers**: Whole numbers that can be positive, negative, or zero (..., -2, -1, 0, 1, 2, ...).\n4. **Rational Numbers**: Numbers that can be expressed as a fraction of two integers (e.g., 1/2, 3/4).\n5. **Irrational Numbers**: Numbers that cannot be expressed as a simple fraction (e.g., \u221a2, \u03c0).\n6. **Real Numbers**: All rational and irrational numbers.\n7. **Complex Numbers**: Numbers that include a real part and an imaginary part (e.g., 3 + 4i).\n\nIf you have a specific aspect of numbers you would like to explore further, please let me know!" }, { "role": "user", "content": "thank you" }, { "role": "assistant", "content": "Could you please clarify your question or provide more details about what you're looking for? I'm here to help!" }, { "role": "user", "content": "what is integration?" }, { "role": "assistant", "content": "Integration is a fundamental concept in calculus that refers to the process of finding the integral of a function. It can be understood in two main contexts:\n\n1. **Definite Integration**: This involves calculating the area under a curve defined by a function over a specific interval. The result is a numerical value that represents this area. For example, the definite integral of a function \\( f(x) \\) from \\( a \\) to \\( b \\) is denoted as:\n \\[\n \\int_{a}^{b} f(x) \\, dx\n \\]\n\n2. **Indefinite Integration**: This refers to finding the antiderivative of a function, which is a function whose derivative is the original function. The result includes a constant of integration (C) because the derivative of a constant is zero. For example, the indefinite integral of \\( f(x) \\) is denoted as:\n \\[\n \\int f(x) \\, dx = F(x) + C\n \\]\n where \\( F(x) \\) is the antiderivative of \\( f(x) \\).\n\nIntegration has numerous applications in mathematics, physics, engineering, and other fields, such as calculating areas, volumes, and solving differential equations.\n\nIf you have any specific questions about integration or its applications, feel free to ask!" }, { "role": "user", "content": "in 5 sentences please summarize your context" }, { "role": "assistant", "content": "The document titled *A First Course in Complex Analysis* is designed for undergraduate students and covers fundamental concepts in complex analysis, including complex numbers, differentiation, integration, and the properties of holomorphic functions. It emphasizes a rigorous approach, introducing series and sequences from scratch, and aims to lead students toward understanding the Residue Theorem and its applications in both continuous and discrete mathematics. The authors, Matthias Beck, Gerald Marchesi, Dennis Pixton, and Lucas Sabalka, have structured the content to be accessible while minimizing reliance on prior real analysis concepts. The book includes numerous examples, exercises, and proofs to reinforce learning and understanding of complex analysis principles. Additionally, it provides insights into the historical context and significance of complex analysis in mathematics." }, { "role": "user", "content": "in 6 sentences please summarize your context" }, { "role": "assistant", "content": "The document titled *A First Course in Complex Analysis* serves as a comprehensive textbook for undergraduate students, focusing on the fundamental concepts of complex analysis. It covers a range of topics, including complex numbers, differentiation, integration, power series, and the properties of holomorphic functions, while minimizing reliance on prior real analysis knowledge. The authors, Matthias Beck, Gerald Marchesi, Dennis Pixton, and Lucas Sabalka, aim to guide students toward understanding significant results such as the Residue Theorem and its applications in both continuous and discrete mathematics. The book is structured to include numerous examples, exercises, and proofs, reinforcing the learning process and providing a rigorous approach to the subject. Additionally, it emphasizes the historical context and significance of complex analysis within the broader field of mathematics. The text is designed to be accessible and engaging, making it suitable for students encountering rigorous analysis for the first time." }, { "role": "assistant", "content": "The document titled *A First Course in Complex Analysis* is designed for undergraduate students and covers essential topics in complex analysis, including complex numbers, differentiation, integration, and the properties of holomorphic functions. It emphasizes a rigorous approach, introducing series and sequences from scratch, and aims to lead students toward understanding significant results such as the Residue Theorem and its applications in both continuous and discrete mathematics. The authors, Matthias Beck, Gerald Marchesi, Dennis Pixton, and Lucas Sabalka, have structured the content to be accessible while minimizing reliance on prior real analysis concepts. The book includes numerous examples, exercises, and proofs to reinforce learning and understanding of complex analysis principles. Additionally, it provides insights into the historical context and significance of complex analysis within the broader field of mathematics. The text is designed to be engaging and informative, making it suitable for students encountering rigorous analysis for the first time." }, { "role": "user", "content": "in 4 sentences please summarize your context" }, { "role": "assistant", "content": "*A First Course in Complex Analysis* is a textbook designed for undergraduate students, focusing on the foundational concepts of complex analysis, including complex numbers, differentiation, integration, and the properties of holomorphic functions. The authors, Matthias Beck, Gerald Marchesi, Dennis Pixton, and Lucas Sabalka, aim to provide a rigorous yet accessible introduction, minimizing reliance on prior real analysis knowledge and treating series and sequences from scratch. The book emphasizes the importance of the Residue Theorem and includes numerous examples, exercises, and proofs to reinforce understanding. Additionally, it highlights the historical context and significance of complex analysis within the broader field of mathematics, making it suitable for students encountering rigorous analysis for the first time." }, { "role": "user", "content": "in 5 sentences please summarize your context" }, { "role": "assistant", "content": "The document titled *A First Course in Complex Analysis* is a comprehensive textbook aimed at undergraduate students, focusing on the fundamental concepts of complex analysis. It covers a wide range of topics, including complex numbers, differentiation, integration, power series, and the properties of holomorphic functions, while minimizing reliance on prior real analysis knowledge. The authors, Matthias Beck, Gerald Marchesi, Dennis Pixton, and Lucas Sabalka, emphasize a rigorous yet accessible approach, incorporating numerous examples, exercises, and proofs to reinforce understanding. The book also explores significant results such as the Residue Theorem and its applications, providing insights into the historical context and importance of complex analysis in mathematics. Overall, it serves as a foundational resource for students encountering rigorous analysis for the first time, preparing them for further studies in mathematics and related fields." }, { "role": "user", "content": "in 5 sentences what is complex numbers?" }, { "role": "assistant", "content": "Complex numbers are an extension of the real numbers, defined as ordered pairs of real numbers, typically expressed in the form \\( z = x + iy \\), where \\( x \\) is the real part, \\( y \\) is the imaginary part, and \\( i \\) is the imaginary unit satisfying \\( i^2 = -1 \\). This formulation allows for the representation of numbers that cannot be expressed as real numbers, such as the square root of negative numbers, thereby providing solutions to equations like \\( x^2 + 1 = 0 \\). Complex numbers can be added, subtracted, multiplied, and divided (except by zero), following algebraic rules similar to those of real numbers, which include properties like commutativity and associativity. Geometrically, complex numbers can be represented as points or vectors in a two-dimensional plane, known as the complex plane, where the x-axis represents the real part and the y-axis represents the imaginary part. The introduction of complex numbers not only enriches the number system but also plays a crucial role in various fields of mathematics, physics, and engineering, particularly in solving polynomial equations and analyzing waveforms." }, { "role": "user", "content": "in 6 sentences what is complex numbers?" }, { "role": "assistant", "content": "" } ], "stream": true, "language_level": "", "chat_channel": ":3990:1726563401443", "language": "German", "tone": "neutral", "writing_style": "standard", "model": "gpt-4o-mini-2024-07-18", "knowledgebase": "ki-dev-large", "seed": 1055, "client_id": 1726563401443, "all_context": false, "follow_up_for": null, "knowledgebase_files_count": 1, "override_command": null, "disable_clarity_check": false, "custom_primer": "", "logging": true, "query_route": "" } INITIALIZATION Knowledgebase: ki-dev-large Base Query: in 6 sentences what is complex numbers? Model: gpt-4o-mini-2024-07-18 Use Curl?: None ================================================== **Elapsed Time: 0.00 seconds** ================================================== ROUTING Query type: summary ================================================== **Elapsed Time: 1.65 seconds** ================================================== RAG PARAMETERS Max Context To Include: 100 Lowest Score to Consider: 0.1 ================================================== **Elapsed Time: 0.14 seconds** ================================================== VECTOR SEARCH ALGORITHM TO USE Use MMR search?: True Use Similarity search?: False ================================================== **Elapsed Time: 0.10 seconds** ================================================== VECTOR SEARCH DONE ================================================== **Elapsed Time: 6.47 seconds** ================================================== PRIMER Primer: You are Simon, a highly intelligent personal assistant in a system called KIOS. You are a chatbot that can read knowledgebases through the "CONTEXT" that is included in the user's chat message. Your role is to act as an expert at summarization and analysis. In your responses to enterprise users, prioritize clarity, trustworthiness, and appropriate formality. Be honest by admitting when a topic falls outside your scope of knowledge, and suggest alternative avenues for obtaining information when necessary. Make effective use of chat history to avoid redundancy and enhance response relevance, continuously adapting to integrate all necessary details in your interactions. Use as much tokens as possible to provide a detailed response. ================================================== **Elapsed Time: 0.17 seconds** ================================================== FINAL QUERY Final Query: CONTEXT: ########## File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 3 Context: # "And what is the use of a book," thought Alice, "without pictures or conversations?" Lewis Carroll (Alice in Wonderland) ## About this book *A First Course in Complex Analysis* was written for a one-semester undergraduate course developed at Binghamton University (SUNY) and San Francisco State University, and has been adopted at several other institutions. For many of our students, Complex Analysis is their first rigorous analysis (if not mathematics) class they take, and this book reflects this very much. We tried to rely on as few concepts from real analysis as possible. In particular, series and sequences are treated from scratch, which has the consequence that power series are introduced late in the course. The goal our book works toward is the Residue Theorem, including some nontraditional applications from both continuous and discrete mathematics. A printed paperback version of this open textbook is available from Orthogonal Publishing (www.orthogonalpublishing.com) or your favorite online bookseller. ## About the authors **Matthias Beck** is a professor in the Mathematics Department at San Francisco State University. His research interests are in geometric combinatorics and analytic number theory. He is the author of three other books, *Computing the Continuous Discretion: Integer-point Enumeration in Polyhedra* (with Sinal Robins, Springer 2007), *The Art of Proof: Basic Training for Mathematics* (with Ross Geoghegan, Springer 2010), and *Combinatorial Reciprocity Theorem: An Invitation to Enumerative Geometric Combinatorics* (with Raman Sanyal, AMS 2018). **Gerald M. Green** is a lecturer in the Department of Mathematical Sciences at Binghamton University (SUNY). **Dennis P. Stinson** is a professor emeritus in the Department of Mathematical Sciences at Binghamton University (SUNY). His research interests are in dynamical systems and formal languages. **Lucas Sabalka** is an applied mathematician at a technology company in Lincoln, Nebraska. He works on 3-dimensional computer vision applications. He was formerly a professor of mathematics at St. Louis University, after postdoctoral positions at UC Davis and Binghamton University (SUNY). His mathematical research interests are in geometric group theory, low dimensional topology, and computational algebra. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 5 Context: # Contents 1. **Complex Numbers** 1.1. Definitions and Algebraic Properties . . . . . . . . 2 1.2. From Algebra to Geometry and Back . . . . . . . . 5 1.3. Geometric Properties . . . . . . . . . . . . . . . . 9 1.4. Elementary Topology of the Plane . . . . . . . . . 12 Optional Lab . . . . . . . . . . . . . . . . . . . . . . 21 2. **Differentiation** 2.1. Limits and Continuity . . . . . . . . . . . . . . . . 23 2.2. Differentiability and Holomorphicity . . . . . . . 28 2.3. The Cauchy–Riemann Equations . . . . . . . . . . . 32 2.4. Constant Functions . . . . . . . . . . . . . . . . . 36 3. **Examples of Functions** 3.1. Möbius Transformations . . . . . . . . . . . . . . . 43 3.2. Infinity and the Cross Ratio . . . . . . . . . . . 46 3.3. Stereographic Projection . . . . . . . . . . . . . . 48 3.4. Exponential and Trigonometric Functions . . . . . 55 3.5. Logarithms and Complex Exponentials . . . . . . . 59 4. **Integration** 4.1. Definition and Basic Properties . . . . . . . . . . 71 4.2. Antiderivatives . . . . . . . . . . . . . . . . . . 76 4.3. Cauchy’s Theorem . . . . . . . . . . . . . . . . . 80 4.4. Cauchy’s Integral Formula . . . . . . . . . . . . 85 5. **Consequences of Cauchy’s Theorem** 5.1. Variations of a Theme . . . . . . . . . . . . . . . 97 5.2. Antiderivatives Again . . . . . . . . . . . . . . 100 5.3. Taking Cauchy's Formulas to the Limit . . . . . . 102 #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 7 Context: # Chapter 1 ## Complex Numbers Die ganzen Zahlen hat der liebe Gott geschaffen, alles andere ist Menschenwerk. (God created the integers, everything else is made by humans.) Leopold Kronecker (1823–1891) The real numbers have many useful properties. There are operations such as addition, subtraction, and multiplication, as well as division by any nonzero number. There are useful laws that govern these operations, such as the commutative and distributive laws. We can take limits and do calculus, differentiating and integrating functions. But you cannot take a square root of \(-1\); that is, you cannot find a real root of the equation $$ x^2 + 1 = 0. \tag{1.1} $$ Most of you have heard that there is a "new" number that is a root of (1.1); that is, \(x^2 + 1 = 0\) or \(x^2 = -1\). We will show that when the real numbers are enlarged to a new system called the **complex numbers**, which includes \(i\), not only do we gain numbers with interesting properties, but we do not lose many of the nice properties that we had before. The complex numbers, like the real numbers, will have the operations of addition, subtraction, multiplication, as well as division by any complex number except zero. These operations will follow all the laws that we are used to, such as the commutative and distributive laws. We will also be able to take limits and do calculus. And there will be a root of (1.1). As a brief historical aside, complex numbers did not originate with the search for a square root of \(-1\); rather, they were introduced in the context of cubic equations. Scipione del Ferro (1465–1526) and Niccolò Tartaglia (1499–1557) discovered a way to find a root of any cubic polynomial, which was publicized by Gerolamo Cardano (1501–1576) and is often referred to as **Cardano's formula**. For the cubic polynomial \(x^3 + px + q\), Cardano's formula involves the quantity $$ \sqrt[3]{-\frac{q}{2} + \sqrt{\left(\frac{q}{2}\right)^2 + \left(\frac{p}{3}\right)^3}} + \sqrt[3]{-\frac{q}{2} - \sqrt{\left(\frac{q}{2}\right)^2 + \left(\frac{p}{3}\right)^3}}. $$ #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 8 Context: ``` # Complex Numbers It is not hard to come up with examples for \( p \) and \( q \) for which the argument of this square root becomes negative and thus not computable within the real numbers. On the other hand (e.g., by arguing through the graph of a cubic polynomial), every cubic polynomial has at least one real root. This seeming contradiction can be solved using complex numbers, as was probably first exemplified by Rafael Bombelli (1526–1572). In the next section we show exactly how the complex numbers are set up, and in the rest of this chapter we will explore the properties of the complex numbers. These properties will be of both algebraic (such as the commutative and distributive properties mentioned already) and geometric nature. You will see, for example, that multiplication can be described geometrically. In the rest of the book, the calculus of complex numbers will be built on the properties that we develop in this chapter. ## 1.1 Definitions and Algebraic Properties There are many equivalent ways to think about a complex number, each of which is useful in its own right. In this section, we begin with a formal definition of a complex number. We then interpret this formal definition in more useful and easier-to-work-with algebraic language. Later we will see several more ways of thinking about complex numbers. **Definition.** The complex numbers are pairs of real numbers: \[ C = \{(x, y) : x, y \in \mathbb{R} \} \] equipped with the addition \[ (x, y) + (a, b) = (x + a, y + b) \quad (1.2) \] and the multiplication \[ (x, y) \cdot (a, b) = (x a - y b, x b + y a) \quad (1.3) \] One reason to believe that the definitions of these binary operations are acceptable is that \( C \) is an extension of \( \mathbb{R} \), in the sense that the complex numbers of the form \((x, 0)\) behave just like real numbers: \[ (x, 0) + (y, 0) = (x + y, 0) \quad \text{and} \quad (x, 0) \cdot (y, 0) = (xy, 0). \] ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 9 Context: So we can think of the real numbers being embedded in \( \mathbb{C} \) as those complex numbers whose second coordinate is zero. The following result states the algebraic structure that we established with our definitions. ## Proposition 1.1 Let \( (x, y) \) be a field, that is, for all \( (a, b) \in \mathbb{C} \): 1. \( (x, y) + (a, b) \in \mathbb{C} \) (1.4) 2. \( (x, y) + (a, d) + (b, c) = (x, y) + ((a + b), c) \) (1.5) 3. \( (x, y) + (0, 0) = (x, y) \) (1.6) 4. \( (x, y) + (-x, -y) = (0, 0) \) (1.7) 5. \( (a, b) + (c, d) = (x, y) \cdot (a, b) + (c, d) \) (1.8) 6. \( (x, y) \in \mathbb{C} \) (1.9) 7. \( (x, y) \cdot (a, b) = (x \cdot a, y \cdot b) \) (1.10) 8. \( (x, y) \cdot (b, d) = (x \cdot b, (a \cdot b)(c, d)) \) (1.11) 9. \( (x, y) \cdot (a, b) = (x, y) \) (1.12) 10. \( (x, y) \cdot (1, 0) = (x, y) \) (1.13) 11. For all \( (x, y) \in \mathbb{C} \setminus \{(0, 0)\} \): \( (x, y) \cdot \left( \frac{(y, -x)}{x^2 + y^2} \right) = (1, 0) \) (1.14) What we are stating here can be compressed in the language of algebra: equations (1.4)–(1.8) say that \( (\mathbb{C}, +) \) is an Abelian group with identity \( (0, 0) \); equations (1.10)–(1.14) say that \( (\mathbb{C} \setminus \{(0, 0)\}, \cdot) \) is an Abelian group with identity \( (1, 0) \). The proof of Proposition 1.1 is straightforward but nevertheless makes for good practice (Exercise 1.14). We give one sample: **Proof (1.18)**. By our definition for complex addition and properties of additive inverse in \( \mathbb{R} \): \[ (x, y) + (-x, -y) = (x + (-x), y + (-y)) = (0, 0). \] The definition of our multiplication implies the innocent-looking statement: \[ (0, 1) \cdot (1, 0) = (1, 0). \quad (1.15) \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 10 Context: ``` # Complex Numbers This identity together with the fact that $$ (x_0, \cdots, x_n) \cdot (x, y) = (ax, az) $$ allows an alternative notation for complex numbers. The latter implies that we can write $$ (x, y) = (x_0, 0) + (0, y) = (x_0, 0) + (0, 1)(0, y). $$ If we think—in the spirit of our remark about embedding R into C—of (x, 0) and (y, 0) as the real numbers x and y, then this means that we can write any complex number (x, y) as a linear combination of (1, 0) and (0, 1), with the real coefficients x and y. Now (1, 0), in turn, can be thought of as the real number 1. So if we give (0, 1) a special name, say i, then the complex number that we used to call (x, y) can be written as $$ x + iy. $$ ### Definition The number x is called the **real part** and y the **imaginary part** of the complex number x + iy, often denoted as Re(x + iy) = x and Im(x + iy) = y. The identity (1.15) then reads $$ i^2 = -1. $$ In fact, much more can now be said with the introduction of the square root of -1. It is not just that (1.1) has a root, but every nonconstant polynomial has roots in C: ### Fundamental Theorem of Algebra (see Theorem 5.11). Every nonconstant polynomial of degree d has d roots (counting multiplicity) in C. The proof of this theorem requires some (important) machinery, so we defer its proof and an extended discussion of it to Chapter 5. We invite you to check that the definitions of our binary operations and Proposition 1.1 are coherent with the usual real arithmetic rules if we think of complex numbers as given in the form x + iy. *The names have historical reasons: people thought of complex numbers as unreal, imagined.* ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 11 Context: # 1.2 From Algebra to Geometry and Back Although we just introduced a new way of writing complex numbers, let’s for a moment return to the \((x, y)\)-notation. It suggests that we can think of a complex number as a two-dimensional real vector. When plotting these vectors in the plane \(\mathbb{R}^2\), we will call the \(x\)-axis the real axis and the \(y\)-axis the imaginary axis. The addition that we defined for complex numbers resembles vector addition; see Figure 1.1. The analogy stops at multiplication: there is no “usual” multiplication of two vectors in \(\mathbb{R}^2\) that gives another vector, and certainly not one that agrees with our definition of the product of two complex numbers. ![Figure 1.1: Addition of complex numbers.](#) Any vector in \(\mathbb{R}^2\) is defined by its two coordinates. On the other hand, it is also determined by its length and the angle it encloses with, say, the positive real axis; let’s define these concepts thoroughly. ### Definition The absolute value (also called the modulus) of \(z = x + iy\) is \[ r = |z| = \sqrt{x^2 + y^2}, \] and an argument of \(z = x + iy\) is a number \(\phi \in \mathbb{R}\) such that \[ x = r \cos \phi \quad \text{and} \quad y = r \sin \phi. \] A given complex number \(z = x + iy\) has infinitely many possible arguments. For instance, the number \(1 = 1 + 0i\) lies on the positive real axis, and has argument \(0\), but we could just as well say it has argument \(2\pi, -2\pi, \text{or } 2k\pi\) for any integer \(k\). The number \(0 = 0 + 0i\) has modulus \(0\), and every real number \(y\) is an argument. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 12 Context: # COMPLEX NUMBERS Aside from the exceptional case of 0, for any complex number \( z \), the arguments of \( z \) all differ by a multiple of \( 2\pi \), just as we saw for the example \( z = 1 \). The absolute value of the difference of two vectors has a nice geometric interpretation: ## Proposition 1.2 Let \( z_1, z_2 \in \mathbb{C} \) be two complex numbers, thought of as vectors in \( \mathbb{R}^2 \), and let \( d(z_1, z_2) \) denote the distance between the endpoints of the two vectors in \( \mathbb{R}^2 \) (see Figure 1.2). Then \[ d(z_1, z_2) = |z_1 - z_2| = |z_2 - z_1|. \] **Proof:** Let \( z_1 = x_1 + iy_1 \) and \( z_2 = x_2 + iy_2 \). From geometry, we know that \[ d(z_1, z_2) = \sqrt{(x_1 - x_2)^2 + (y_1 - y_2)^2}. \] This is the definition of \( |z_1 - z_2| \). Since \( (x_1 - x_2) = (x_2 - x_1) \) and \( (y_1 - y_2) = (y_2 - y_1) \), this is also equal to \( |z_2 - z_1| \. \qed ![Figure 1.2: Geometry behind the distance between two complex numbers.](path_to_image) That \( |z_1 - z_2| = |z_2 - z_1| \) simply says that the vector from \( z_2 \) to \( z_1 \) has the same length as the vector from \( z_1 \) to \( z_2 \). One reason to introduce the absolute value and argument of a complex number is that they allow us to give a geometric interpretation for the multiplication of two complex numbers. Let’s say we have two complex numbers \( z_1 = x_1 + iy_1 \), with absolute value \( r_1 \) and argument \( \phi_1 \), and \( z_2 = x_2 + iy_2 \), with absolute value \( r_2 \) and argument \( \phi_2 \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 13 Context: # FROM ALGEBRA TO GEOMETRY AND BACK ## 7 ϕ₂. This means we can write \(x_1 + iy_1 = (r_1 \cos \phi_1) + i(r_1 \sin \phi_1)\) and \(x_2 + iy_2 = (r_2 \cos \phi_2) + i(r_2 \sin \phi_2)\). To compute the product, we make use of some classic trigonometric identities: \[ (x_1 + iy_1)(x_2 + iy_2) = (r_1 \cos \phi_1 + ir_1 \sin \phi_1)(r_2 \cos \phi_2 + ir_2 \sin \phi_2) \] \[ = r_1 r_2 (\cos \phi_1 \cos \phi_2 - \sin \phi_1 \sin \phi_2) + i(r_1 r_2 \cos \phi_2 \sin \phi_1 + r_1 r_2 \sin \phi_2 \cos \phi_1) \] \[ = r_1 r_2 \left( \cos(\phi_1 + \phi_2) + i \sin(\phi_1 + \phi_2) \right). \] So the absolute value of the product is \(r_1 r_2\) and one of its arguments is \(ϕ_1 + ϕ_2\). Geometrically, we are multiplying the lengths of the two vectors representing our two complex numbers and adding their angles measured with respect to the positive real axis. ![Figure 1.3: Multiplication of complex numbers](#) In view of the above calculation, it should come as no surprise that we will have to deal with quantities of the form \(x + iy\) (where \(y\) is some real number) quite a bit. To save space, bytes, ink, etc., and because "Mathematics is for lazy people" we introduce a shortcut notation and define: \[ e^{i\phi} = \cos \phi + i \sin \phi. \] ^1 You should convince yourself that there is no problem with this fact since there are many possible arguments for complex numbers, as both cosine and sine are periodic functions with period \(2\pi\). ^2 Peter Halton (unpublished articles, Hudson River Undergraduate Mathematics Conference 2000). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 14 Context: # COMPLEX NUMBERS Figure 1.4 shows three examples. At this point, this exponential notation is indeed ![Figure 1.4: Three sample complex numbers of the form \( e^{x} \).](image-path) purely a notation. We will later see in Chapter 3 that it has an intimate connection to the complex exponential function. For now, we motivate this maybe strange seeming definition by collecting some of its properties: ## Proposition 1.3. For any \( x_1, x_2 \in \mathbb{R} \): 1. \( e^{(x_1 + x_2 i)} = e^{x_1} e^{x_2 i} \) 2. \( e^{0} = 1 \) 3. \( \frac{d}{dx} e^{x} = e^{x} \) 4. \( |e^{x}| = 1 \) 5. \( e^{i\pi} = -1 \) You are encouraged to prove them (Exercise 1.16); again, we give a sample. ## Proof of \( e^{x} \). By definition of \( e^{x} \): \[ \frac{d}{dx} e^{(x + i)} = -\sin{(x)} + \cos{(x)} = i ( \cos{(x)} + i\sin{(x)}) = i e^{(x+i)} \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 15 Context: # Geometric Properties Proposition 1.3 implies that \( z^{n} = 1 \) for any integers \( n \) and \( r > 0 \). Thus, numbers of the form \( z^{n} \) with \( z \in \mathbb{Q} \) play a pivotal role in solving equations of the form \( z^{n} = 1 \)—plenty of reason to give them a special name. **Definition.** A root of unity is of the form \( z^{n} \) for some integers \( n \) and \( r > 0 \). A root of unity \( z \) is a complex number \( z \) such that \( z^{n} = 1 \) for some positive integer \( n \). In this case, we call \( z \) an \( n \)th root of unity. If \( n \) is the smallest positive integer with the property \( z^{n} = 1 \), then \( z \) is a primitive \( n \)th root of unity. **Example 1.4.** The 4th roots of unity are \( 1 \) and \( i \) and \( e^{i\frac{\pi}{2}} \). The latter two are primitive 4th roots of unity. With our new notation, the sentence "the complex number \( x + iy \) has absolute value \( r \) and argument \( \theta \) now becomes the identity \[ x + iy = r e^{i\theta}. \] The left-hand side is often called the **rectangular form**, the right-hand side the **polar form** of this complex number. We now have five different ways of thinking about a complex number: the formal definition, in rectangular form, in polar form, and geometrically, using Cartesian coordinates or polar coordinates. Each of these five ways is useful in different situations, and translating between them is an essential ingredient in complex analysis. The five ways and their corresponding notation are listed in Figure 1.5. This list is not exhaustive; see, e.g., Exercise 1.21. ## 1.3 Geometric Properties From the chain of basic inequalities \[ -\sqrt{x^{2} + y^{2}} \leq -|z| \leq \sqrt{x^{2} + y^{2}} \leq |z| \leq \sqrt{x^{2} + y^{2}}, \] (or, alternatively, by arguing with basic geometric properties of triangles), we obtain the inequalities \[ -|z| \leq \text{Re}(z) \leq |z| \] and \[ -|z| \leq \text{Im}(z) \leq |z|. \tag{1.16} \] The square of the absolute value has the nice property \[ |x + iy|^{2} = x^{2} + y^{2} = (x + iy)(x - iy). \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 16 Context: # COMPLEX NUMBERS | | Algebraic | Geometric | Exponential | |------------|------------------|------------------|---------------| | Formal | \(x + iy\) | Cartesian | \(re^{i\theta}\) | | | Rectangular | \(x\) | Polar | | | | \(y\) | | **Figure 1.5:** Five ways of thinking about a complex number. This is one of many reasons to give the process of passing from \(x + iy\) to \(x - iy\) a special name. ## Definition The number \(x - iy\) is the (complex) conjugate of \(x + iy\). We denote the conjugate by \[ x + iy = x - iy. \] Geometrically, conjugating \(z\) means reflecting the vector corresponding to \(z\) with respect to the real axis. The following collects some basic properties of the conjugate. ## Proposition 1.5 For any \(z_1, z_2, z_3 \in \mathbb{C}\): 1. \(z_1 \overline{z_2} = \overline{z_1 z_2}\) 2. \(\overline{z_1 z_2} = \overline{z_2} \overline{z_1}\) 3. \(\overline{\left(\frac{z_1}{z_2}\right)} = \frac{\overline{z_2}}{\overline{z_1}}\) 4. \(\overline{z} = z\) 5. \(|z| = |z|\) The proofs of these properties are easy (Exercise 1.22); once more we give a sample. ### Proof of (b) Let \(z_1 = x_1 + iy_1\) and \(z_2 = x_2 + iy_2\). Then \[ z_1 z_2 = (x_1 + iy_1)(x_2 + iy_2) = (x_1x_2 - y_1y_2) + i(x_1y_2 + y_1x_2) = \overline{z_1} \overline{z_2}. \] Image Analysis: ### 1. Localization and Attribution - **Page**: This is a page from a document or book, numbered at the top left as "10." - **Image 1**: An illustrated table at the top of the page labeled as "Figure 1.5." - **Text Block**: Multiple paragraphs of text underneath the table, including definitions, propositions, and proofs. ### 2. Object Detection and Classification - **Image 1:** - **Objects**: A table with three rows and three columns. - **Categories**: Types of complex number representations. - **Key Features**: - **Row 1**: "Formal" corresponds to (x, y). - **Row 2**: "Algebraic" includes rectangular (x + iy) and exponential (re^iθ). - **Row 3**: "Geometric" includes cartesian and polar representations. ### 3. Scene and Activity Analysis - **Scene**: - The scene depicts a page from a textbook or academic document. - The key activity is educational content delivery, specifically discussing complex numbers. ### 4. Text Analysis - **Detected Text**: - Title: "COMPLEX NUMBERS." - Sections: - "Figure 1.5: Five ways of thinking..." - Definitions and propositions related to complex numbers. - Proof of a property. - **Analysis**: - The page discusses different representations of complex numbers, highlights their properties, and presents relevant mathematical proofs. ### 5. Diagram and Chart Analysis - **Image 1:** - **Content**: The table categorizes the representations of complex numbers. - **Axes/Scales**: Not applicable. - **Legends**: Explanatory text within the cells. - **Key Insights**: - Complex numbers can be represented in multiple forms: formal, algebraic, geometric. - The table is a clear and concise way to present these different perspectives. ### 6. Product Analysis - **Not applicable**: No products were depicted in the image. ### 7. Anomaly Detection - **Not applicable**: No anomalies in the visual content. ### 8. Color Analysis - **Dominant Colors**: Black text on a white background. - **Impact**: Standard colors for printed or digital educational content, aiding readability and focus. ### 9. Perspective and Composition - **Perspective**: Straight-on view, typical for document pages. - **Composition**: - The table (Image 1) is at the top, drawing initial attention. - Subsequent text follows a structured format, typical of academic documents. ### 10. Contextual Significance - **Contribution**: - The image and text provide fundamental knowledge about complex numbers. - It enriches the educational material by categorizing and defining complex number representations. ### 11. Metadata Analysis - **Not available**: No metadata provided from the image. ### 12. Graph and Trend Analysis - **Not applicable**: No graphs present. ### 13. Graph Numbers - **Not applicable**: No graphs present. ### Additional Aspects - **Process Flows and Descriptions**: - A defined process for understanding the conjugate of a complex number. - Steps to prove a proposition about complex numbers. - **Type Designations**: - Designates formal, algebraic, and geometric types of complex number representations. - **Trend and Interpretation**: - Emphasizes the versatility and various intuitions behind complex number representations. - **Tables**: - The table encapsulates the five types of complex number representations succinctly. This comprehensive examination focuses on the detailed aspects and provides a thorough understanding of the educational content on the described page. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 17 Context: # GEOMETRIC PROPERTIES We note that \( f(z) \) yields a neat formula for the inverse of a nonzero complex number, which is implicit already in (1.14): \[ z^{-1} = \frac{1}{|z|^2} \overline{z}. \] A famous geometric inequality (which holds, more generally, for vectors in \( \mathbb{R}^n \)) goes as follows. ## Proposition 1.6 (Triangle Inequality) For any \( z_1, z_2 \in \mathbb{C} \) we have \( |z_1 + z_2| \leq |z_1| + |z_2| \). By drawing a picture in the complex plane, you should be able to come up with a geometric proof of the triangle inequality. Here we proceed algebraically: ### Proof We make extensive use of Proposition 1.5: \[ |z_1 + z_2|^2 = |(z_1 + z_2)(\overline{z_1 + z_2})| = z_1\overline{z_1} + z_1\overline{z_2} + z_2\overline{z_1} + z_2\overline{z_2} = |z_1|^2 + z_1\overline{z_2} + z_2\overline{z_1} + |z_2|^2 \] \[ \leq |z_1|^2 + 2\Re(z_1\overline{z_2}) + |z_2|^2 \] \[ = |z_1|^2 + |z_2|^2 + 2|z_1||z_2| \cdot \frac{\Re(z_1\overline{z_2})}{|z_1||z_2|} \leq (|z_1| + |z_2|)^2, \] where the inequality follows from (1.16). Taking square roots on the left- and right-hand sides proves our claim. For future reference we list several useful variants of the triangle inequality: ## Corollary 1.7 For \( z_1, z_2, \ldots, z_n \in \mathbb{C} \), we have the following relations: (a) The triangle inequality: \( |z_1 + z_2| \leq |z_1| + |z_2|. \) (b) The reverse triangle inequality: \( |z_1 + z_2| \geq ||z_1| - |z_2||. \) (c) The triangle inequality for sums: \[ \left| \sum_{k=1}^{n} z_k \right| \leq \sum_{k=1}^{n} |z_k|. \] Inequality (a) is just a rewrite of the original triangle inequality, using the fact that \( |z| = |z| \) and follows by induction. The proof of the reverse triangle inequality (b) is left as Exercise 1.25. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 18 Context: # 1.4 Elementary Topology of the Plane In Section 1.2 we saw that the complex numbers \( C \), which were initially defined algebraically, can be identified with the points in the Euclidean plane \( \mathbb{R}^2 \). In this section we collect some definitions and results concerning the topology of the plane. \[ \begin{array}{c} y \\ \text{C}(2+i,2) \\ \hspace{-30pt} \text{D}(-2, 1) \\ \hspace{80pt} 1 \\ \hspace{-30pt} x \end{array} \] **Figure 1.6:** Sample circle and disk. In Proposition 1.2, we interpreted \( |z - w| \) as the distance between the complex numbers \( z \) and \( w \), viewed as points in the plane. So if we fix a complex number \( a \) and a positive real number \( r \), then all \( z \in C \) satisfying \( |z - a| = r \) form the set of points at distance \( r \) from \( a \); this set is the circle with center \( a \) and radius \( r \), which we denote by \[ C(a, r) = \{ z \in C : |z - a| = r \} \] The inside of this circle is called the open disk with center \( a \) and radius \( r \); we use the notation \[ D(a, r) = \{ z \in C : |z - a| < r \} \] Note that \( D(a, r) \) does not include the points on \( C(a, r) \). Figure 1.6 illustrates these definitions. Next we need some terminology for talking about subsets of \( C \). **Definition.** Suppose \( G \) is a subset of \( C \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 20 Context: # Complex Numbers ![Figure 1.7: The intervals [0,1) and (1,2) are separated.](image_link) ## Definition Two sets \( X, Y \subset \mathbb{C} \) are separated if there are disjoint open sets \( A, B \subset C \) so that \( X \subset A \) and \( Y \subset B \). A set \( G \subset \mathbb{C} \) is connected if it is impossible to find two separated nonempty sets whose union is \( G \). A region is a connected open set. The idea of separation is that the two open sets \( A \) and \( B \) ensure that \( X \) and \( Y \) cannot just "stick together." It is usually easy to check that a set is not connected. On the other hand, it is hard to use the above definition to show that a set is connected, since we have to rule out any possible separation. ## Example 1.10 The intervals \( X = [0,1) \) and \( Y = (1,2) \) on the real axis are separated: There are infinitely many choices for \( A \) and \( B \) that work; one choice is \( A = D[0,1) \) and \( B = D(1,2) \), depicted in Figure 1.7. Hence \( X \cup Y = [0,1) \cup (1,2) \) is not connected. One type of connected set that we will use frequently is a path. ## Definition A path (or curve) in \( \mathbb{C} \) is a continuous function \( \gamma : [a,b] \to \mathbb{C} \), where \([a,b]\) is a closed interval in \( \mathbb{R} \). We may think of \( \gamma \) as a parametrization of the image that is painted by the path and will often write this parametrization as \( \gamma(t) \), for \( a \leq t \leq b \). The path is smooth if it is differentiable and the derivative \( \gamma' \) is continuous and nonzero. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 21 Context: # ELEMENTARY TOPOLOGY OF THE PLANE This definition uses the calculus notions of continuity and differentiability; that is, \( \gamma: [a, b] \to C \) being continuous means that for all \( t_0 \in [a, b] \) \[ \lim_{t \to t_0} \gamma(t) = \gamma(t_0) \] and the derivative of \( \gamma \) at \( t_0 \) is defined by \[ \gamma'(t_0) = \lim_{t \to t_0} \frac{\gamma(t) - \gamma(t_0)}{t - t_0} \] \[ \gamma_1(t) = -2 + 2e^{it}, \quad 0 \leq t \leq 2\pi \] \[ \gamma_2(t) = \begin{cases} 3 + i(t - 2) & \text{if } 0 \leq t \leq 3 \\ 6 - i + i(t - 1) & \text{if } 3 < t \leq 5 \end{cases} \] Figure 1.8: Two paths and their parameterizations: \( \gamma_1 \) is smooth and \( \gamma_2 \) is continuous and piecewise smooth. Figure 1.8 shows two examples. We remark that each path comes with an orientation, i.e., a sense of direction. For example, the path \( \gamma_1 \) in Figure 1.8 is different from \[ \gamma_1(t) = -2 + 2e^{it}, \quad 0 \leq t \leq \frac{3\pi}{2} \] even though both \( \gamma_1 \) and \( \gamma_3 \) yield the same picture; \( \gamma_1 \) features a counter-clockwise orientation, where as that of \( \gamma_2 \) is clockwise. It is a customary and practical abuse of notation to use the same letter for the path and its parameterization. We emphasize that a path must have a parameterization, and that the parameterization must be defined and continuous on a closed and bounded interval \([a, b]\). Since topologically we may identify \( C \) with \( \mathbb{R}^2 \), a path can be specified. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 22 Context: ``` # Complex Numbers by giving two continuous real-valued functions of a real variable, \( x(t) \) and \( y(t) \), and setting \( y(t) = x(t) + iy(t) \). ## Definition The path \( \gamma: [a, b] \to C \) is simple if \( \gamma(t_1) = \gamma(t_2) \) is one-to-one, with the possible exception that \( \gamma(a) = \gamma(b) \) in plain English: the path does not cross itself. A path \( \gamma: [a, b] \to C \) is closed if \( \gamma(a) = \gamma(b) \). ## Example 1.11 The unit circle \( C[0,1] \), parametrized, e.g., by \( \gamma(t) = e^{it} \), \( 0 \leq t < 2\pi \), is a simple closed path. As seems intuitively clear, any path is connected; however, a proof of this fact requires a bit more preparation in topology. The same goes for the following result, which gives a useful property of open connected sets. ## Theorem 1.12 If any two points in \( G \subset C \) can be connected by a path in \( G \), then \( G \) is connected. Conversely, if \( G \subset C \) is open and connected, then any two points of \( G \) can be connected by a path in \( G \); in fact, we can connect any two points of \( G \) by a chain of horizontal and vertical segments lying in \( G \). Here a chain of segments in \( G \) means the following: there are points \( z_{0}, z_{1}, \ldots, z_{n} \) such that \( z_{0} \) and \( z_{n} \) are the endpoints of a horizontal or vertical segment in \( G \) for all \( k = 0, 1, \ldots, n-1 \) (it is not hard to parametrize such a chain, so it determines a path). ## Example 1.13 Consider the open unit disk \( D[0, 1) \). Any two points in \( D[0, 1) \) can be connected by a chain of at most two segments in \( D[0, 1) \) and so \( D[0, 1) \) is connected. Now let \( G = (D[0, 1) \setminus \{0\}) \). This is the punctured disk obtained by removing the center from \( D[0, 1) \). Then \( G \) is open and it is connected, but now you may need more than two segments to connect points. For example, you need three segments to connect \( z_{0} \to z_{1} \to z_{2} \) since we cannot go through \( 0 \). We remark that the second part of Theorem 1.12 is not generally true if \( G \) is not open. For example, circles are connected but there is no way to connect two distinct points of a circle by a chain of segments that are subsets of the circle. A more extreme example, discussed in topology texts, is the "topologist's sine curve," which is a connected set \( S \) that contains points that cannot be connected by a path of any sort within \( S \). ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 23 Context: # Exercises ## 1.1. Let \( z = 1 + 2i \) and \( w = 2 - i \). Compute the following: (a) \( z + 3w \) (b) \( w - z \) (c) \( z^2 \) (d) \( \text{Re}(wz + w) \) (e) \( z^2 + z + i \) ## 1.2. Find the real and imaginary parts of each of the following: (a) \( \frac{e^{ia}}{1 + i} \) for any \( a \in \mathbb{R} \) (b) \( 1 - i \) (c) \( \left( \frac{1}{\sqrt{2}} \right)^3 \) (d) \( i^n \) for any \( n \in \mathbb{Z} \) ## 1.3. Find the absolute value and conjugate of each of the following: (a) \( -2 + i \) (b) \( (2 + i\sqrt{3}) \) (c) \( \frac{3}{\sqrt{5}} - \sqrt{5}i \) (d) \( (1 + i)^{6} \) ## 1.4. Write in polar form: (a) \( 2i \) (b) \( 1 + i \) (c) \( 3 + \sqrt{3}i \) (d) \( -i \) (e) \( (2 - i)^2 \) (f) \( [3 - 4i] \) (g) \( \sqrt{5} - i \) (h) \( \left( \frac{1}{4} \right)^{4} \) ## 1.5. Write in rectangular form: (a) \( \sqrt{2}e^{i\frac{\pi}{4}} \) (b) \( 3e^{i\frac{\pi}{6}} \) (c) \( -r^{2}e^{i2\theta} \) (d) \( 2e^{i\frac{\pi}{3}} \) ## 1.6. Write in both polar and rectangular form: (a) \( e^{i\frac{\pi}{6}} \) (b) \( \frac{1}{2} e^{i\theta} \) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 24 Context: # COMPLEX NUMBERS ## 1.7 Show that the quadratic formula works. That is, for \( a, b, c \in \mathbb{R} \) with \( a \neq 0 \), prove that the roots of the equation \( ax^2 + bx + c = 0 \) are \[ x = \frac{-b \pm \sqrt{b^2 - 4ac}}{2a} \] Here we define \( \sqrt{b^2 - 4ac} = i \sqrt{-(b^2 - 4ac)} \) if the discriminant \( b^2 - 4ac \) is negative. ## 1.8 Use the quadratic formula to solve the following equations: - (a) \( x^2 + 25 = 0 \) - (b) \( 2x^2 + 2x + 5 = 0 \) - (c) \( 5x^2 + 4x + 1 = 0 \) - (d) \( x^2 - 2x = 0 \) - (e) \( x^2 = 2x \) ## 1.9 Find all solutions of the equation \( x^2 + 2x + (1-i) = 0 \). ## 1.10 Fix \( a \in \mathbb{C} \) and \( b \in \mathbb{R} \). Show that the equation \( |z|^2 + \text{Re}(z) + b = 0 \) has a solution if and only if \( |a|^2 \geq 4b \). When solutions exist, show the solution set is a circle. ## 1.11 Find all solutions to the following equations: - (a) \( z^6 = 1 \) - (b) \( z^6 = -16 \) - (c) \( z^6 = e^{-3} \) - (d) \( z^6 - z^2 = 0 \) ## 1.12 Show that \( |z| = 1 \) if and only if \( z = \bar{z} \). ## 1.13 Show that: - (a) \( z \) is a real number if and only if \( z = \bar{z} \). - (b) \( z \) is either real or purely imaginary if and only if \( |z|^2 = z^2 \). ## 1.14 Review Proposition 1.1. ## 1.15 Show that if \( z_1 z_2 = 0 \) then \( z_1 = 0 \) or \( z_2 = 0 \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 25 Context: # Elementary Topology of the Plane ## 1.16 Prove Proposition 1.3. ## 1.17 Fix a positive integer \( n \). Prove that the solutions to the equation \( z^n = 1 \) are precisely \( z = e^{2 \pi i k/n} \) where \( k \in \mathbb{Z} \). (Hint: To show that every solution of \( z^n = 1 \) is of this form, first prove that it must be of the form \( z = e^{i \theta} \) for some \( \theta \in \mathbb{R} \), then write \( z = m + ib \) for some integer \( m \) and some real number \( 0 < b < 1 \), and then argue that \( b \) has to be zero.) ## 1.18 Show that \[ z^2 - 1 = (z - 1)\left(z^2 + 2 \cos \frac{\pi}{3}(z^2 - 2z \cos \frac{\pi}{3} + 1\right) \] and deduce from this closed formula for \( \cos \frac{\pi}{3} \) and \( \cos \frac{2\pi}{3} \). ## 1.19 Fix a positive integer \( n \) and a complex number \( w \). Find all solutions to \( z^n = w \). (Hint: Write \( w \) in terms of polar coordinates.) ## 1.20 Use Proposition 1.3 to derive the triple angle formulas: (a) \(\cos(3\phi) = 4\cos^3\phi - 3\cos\phi \sin^2\phi\) (b) \(\sin(3\phi) = 3\cos^2\phi \sin\phi - \sin^3\phi\) ## 1.21 Given \( x, y \in \mathbb{R} \), define the matrix \( M(x, y) = \begin{bmatrix} x & -y \\ y & x \end{bmatrix} \). Show that \[ M(x, y) + M(a, b) = M(x + a, y + b) \] and \[ M(x, y)M(a, b) = M(xa - yb, xb + ya) \] (This means that the set \( \{ M(x, y) : x, y \in \mathbb{R} \} \) equipped with the usual addition and multiplication of matrices, behaves exactly like \( C = \{ (x, y) : x, y \in \mathbb{R} \} \).) ## 1.22 Prove Proposition 1.5. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 26 Context: # COMPLEX NUMBERS ## 1.23 Sketch the following sets in the complex plane: - (a) \( \{ z \in \mathbb{C} : |z - 1 + i| = 1 \} \) - (b) \( \{ z \in \mathbb{C} : |z - 1 + i| \leq 2 \} \) - (c) \( \{ z \in \mathbb{C} : \text{Re}(z^2 + 2 - 2i) = 3 \} \) - (d) \( \{ z \in \mathbb{C} : |z - i| + |z + i| = 3 \} \) - (e) \( \{ z \in \mathbb{C} : |z| = |z - 1| \} \) - (f) \( \{ z \in \mathbb{C} : |z - 1| = 2 |z + 1| \} \) - (g) \( \{ z \in \mathbb{C} : \text{Re}(z) = 1 \} \) - (h) \( \{ z \in \mathbb{C} : \text{Im}(z) = 1 \} \) ## 1.24 Suppose \( \rho \) is a polynomial with real coefficients. Prove that: - (a) \( \rho(\overline{z}) = \overline{\rho(z)} \). - (b) \( \rho(z) = 0 \) if and only if \( \rho(\overline{z}) = 0 \). ## 1.25 Prove the reverse triangle inequality (Proposition 1.7(b)): \[ |z_1 - z_2| \leq |z_1| + |z_2|. \] ## 1.26 Use the previous exercise to show that \[ \left| \frac{1}{z - 2} \right| < \frac{1}{3} \] for every \( z \) on the circle \( C[0,2] \). ## 1.27 Sketch the sets defined by the following constraints and determine whether they are open, closed, or neither; bounded; connected. - (a) \( |z + 3| < 2 \) - (b) \( \text{Im}(z) < 1 \) - (c) \( 0 < |z - 1| < 2 \) - (d) \( |z| = |1 + i| + 2 \) - (e) \( |z| = |1 + i| + 3 \) ## 1.28 What are the boundaries of the sets in the previous exercise? ## 1.29 Let \( G \) be the set of points \( z \in \mathbb{C} \) satisfying either \( z = r \) and \( -2 < r < -1 \), or \( |z| < 1 \), or \( z = \sigma \) where \( \sigma = -2 \). - (a) Sketch the set \( G \), being careful to indicate exactly the points that are in \( G \). - (b) Determine the interior points of \( G \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 27 Context: # Elementary Topology of the Plane 21 (c) Determine the boundary points of \( G \). (d) Determine the isolated points of \( G \). ## 1.30 The set \( G \) in the previous exercise can be written in three different ways as the union of two disjoint nonempty separated subsets. Describe them, and in each case say briefly why the subsets are separated. ## 1.31 Show that the union of two regions with nonempty intersection is itself a region. ## 1.32 Show that if \( A \subset B \) and \( B \) is closed, then \( A \subset B \). Similarly, if \( A \subset B \) and \( A \) is open, show that \( A \) is contained in the interior of \( B \). ## 1.33 Find a parameterization for each of the following paths: (a) The circle \( C(1 + i, 1) \), oriented counter-clockwise (b) The line segment from \( -1 - i \) to \( 2i \) (c) The top half of the circle \( C(0, \frac{3}{4}) \), oriented clockwise (d) The rectangle with vertices \( \pm 1 \pm 2i \), oriented counter-clockwise (e) The ellipse \( \{ z \in \mathbb{C} : |z - 1| + |z + 1| = 4 \} \), oriented counter-clockwise ## 1.34 Draw the path parameterized by \[ \gamma(t) = \cos(t) \cdot \cosh(t) + i \cdot \sin(t) \cdot \sinh(t), \quad 0 \leq t \leq 2\pi. \] ## 1.35 Let \( G \) be the annulus determined by the inequalities \( 2 < |z| < 3 \). This is a connected open set. Find the maximum number of horizontal and vertical segments in \( G \) needed to connect two points of \( G \). --- ### Optional Lab Open your favorite web browser and search for the complex function grapher for the open-source software GeoGebra. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 28 Context: # Complex Numbers 1. Convert the following complex numbers into their polar representation, i.e., give the absolute value and the argument of the number: \[ 3 + 4i = r e^{i\theta} = 2 + 2i = \frac{1}{\sqrt{3 + i}} = \] After you have finished computing these numbers, check your answers with the program. 2. Convert the following complex numbers given in polar representation into their rectangular representation: \[ 2e^{i\theta} = 3e^{i\phi} = \frac{1}{e^{i\varphi}} = -\sqrt{2}e^{2i\phi} = \] After you have finished computing these numbers, check your answers with the program. 3. Pick your favorite five numbers from the ones that you’ve played around with and put them in the tables below, in both rectangular and polar form. Apply the functions listed to your numbers. Think about which representation is more helpful in each instance. | rectangular | polar | |-------------|------------| | z + 1 | | | z + 2 - i | | | 2z | | | -z | | | z^2 | | | Re(z) | | | Im(z) | | | /Im(z) | | | |z| | | | 1/2 | | 4. Play with other examples until you get a feel for these functions. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 29 Context: # Chapter 2 ## Differentiation Mathematical study and research are very suggestive of generalizing. Whispers make several efforts before he climbed the Mathematics in the 1860s and even then it cut the life short of this party. Now, however, any source can be looked up for a small act, and perhaps one does not appreciate the difficulty of the original account. So in mathematics, it may be found hard to realize the great initial difficulty of making a little step which may seem so natural and obvious, and it may not be surprising if such a step has been found and lost again. **Louis Nodel (1888–1972)** We will now start our study of complex functions. The fundamental concept on which all of calculus is based is that of a limit—it allows us to develop the central properties of continuity and differentiability of functions. Our goal in this chapter is to do the same for complex functions. ### 2.1 Limits and Continuity **Definition.** A (complex) function \( f \) is a map from a subset \( G \subset \mathbb{C} \) to \( \mathbb{C} \); in this situation we will write \( f : G \to \mathbb{C} \) and call \( G \) the domain of \( f \). This means that each element \( z \in G \) gets mapped to exactly one complex number, called the image of \( z \) and usually denoted by \( f(z) \). So far there is nothing that makes complex functions any more special than, say, functions from \( \mathbb{R} \) to \( \mathbb{R} \). In fact, we can construct many familiar looking functions from the standard calculus repertoire, such as \( f(z) = z \) (the identity map), \( f(z) = z^2 + 1 \), or \( f(z) = \frac{1}{z} \). The former three could be defined on all of \( \mathbb{C} \), whereas for the latter we have to exclude the origin \( z = 0 \) from the domain. On the other hand, we could construct some functions that make use of a certain representation of \( z \), for example, \( f(x, y) = x - 2iy \), \( f(x, y) = y - i \), or \( f(z, \varphi) = 2r e^{i\varphi} \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 30 Context: Next we define limits of a function. The philosophy of the following definition is not restricted to complex functions, but for sake of simplicity we limit it only for those functions. ## Definition Suppose \( f : G \to \mathbb{C} \) and \( z_0 \) is an accumulation point of \( G \). If \( \epsilon \) is a complex number such that for every \( \delta > 0 \) we can find \( \delta > 0 \) such that \( 0 < |z - z_0| < \delta \), then \[ \lim_{z \to z_0} f(z) = w_0. \] This definition is the same as is found in most calculus texts. The reason we require that \( z_0 \) is an accumulation point of the domain is just that we need to be sure that there are points \( z \) of the domain that are arbitrarily close to \( z_0 \). Just as in the real case, our definition (i.e., the part that says \( 0 < |z - z_0| \)) does not require that \( z_0 \) is in the domain of \( f \); the definition explicitly ignores the value of \( f(z_0) \). ## Example 2.1 Let's prove that \( \lim_{z \to 2} z^2 = 4 \). Given \( \epsilon > 0 \), we need to determine \( \delta > 0 \) such that \( 0 < |z - 2| < \delta \) implies \( |z^2 - 4| < \epsilon \). We rewrite: \[ |z^2 - 4| = |z - 2||z + 2|. \] If we choose \( \delta < 1 \), then the factor \( |z + 2| \) on the right can be bounded by 3 (draw a picture). This means that any \( \delta < \min\{1, \frac{\epsilon}{3}\} \) should do the trick; in this case, \( 0 < |z - 2| < \delta \) implies: \[ |z^2 - 4| < 3 |z - 2| < 3 \delta < \epsilon. \] This proves \( \lim_{z \to 2} z^2 = 4 \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 31 Context: # LIMITS AND CONTINUITY Just as in the real case, the limit \( w \) is unique if it exists (Exercise 2.3). It is often useful to investigate limits by restricting the way the point \( z \) approaches \( w \). The following result is a direct consequence of the definition. ## Proposition 2.2 Suppose \( f: G \rightarrow \mathbb{C} \) and \( \lim_{z \to w} f(z) = w_0 \), where \( w_0 \) is an accumulation point of \( G \). If \( f \) is the restriction of \( g \) to \( G \) then \( \lim_{z \to w} f(z) \) exists and has the value \( w_0 \). The definition of limit in the complex domain has to be treated with a little more care than its real companion; this is illustrated by the following example. ## Example 2.3 The limit of \( z^2 \) as \( z \to 0 \) does not exist. To see this, we try to compute this limit as \( z \to 0 \) on the real and on the imaginary axis. In the first case, we can write \( z = x \) where \( x \in \mathbb{R} \), and then \[ \lim_{x \to 0} \frac{1}{z} = \lim_{x \to 0} \frac{1}{x^2} = \lim_{x \to 0} \frac{1}{x} = 1. \] In the second case, we write \( z = iy \) where \( y \in \mathbb{R} \), and then \[ \lim_{y \to 0} \frac{1}{iy} = \lim_{y \to 0} \frac{-i}{y} = -1. \] So we get a different "limit" depending on the direction from which we approach \( 0 \). Proposition 2.2 then implies that the limit of \( z^2 \) as \( z \to 0 \) does not exist. On the other hand, the following usual limit rules are valid for complex functions; the proofs of these rules are everything but trivial and make for nice practice (Exercise 2.4); as usual, we give a sample proof. ## Proposition 2.4 Let \( f \) and \( g \) be complex functions with domain \( G \), let \( w \) be an accumulation point of \( G \), and let \( c \in \mathbb{C} \). If \( \lim_{z \to w} f(z) \) and \( \lim_{z \to w} g(z) \) exist, then 1. \( \lim_{z \to w} (f(z) + g(z)) = \lim_{z \to w} f(z) + \lim_{z \to w} g(z) \) 2. \( \lim_{z \to w} (f(z) g(z)) = \lim_{z \to w} f(z) \cdot \lim_{z \to w} g(z) \) 3. \( \lim_{z \to w} \left( \frac{f(z)}{g(z)} \right) = \frac{\lim_{z \to w} f(z)}{\lim_{z \to w} g(z)} \) where in the last identity we also require that \( \lim_{z \to w} g(z) \neq 0 \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 37 Context: # Differentiability and Holomorphicity ## Proof Let \( \gamma_1(t) \) and \( \gamma_2(t) \) be parametrizations of the two paths such that \( \gamma_1(0) = \gamma_2(0) = \gamma(0) \). Then \( \gamma_2(t) \) (considered as a vector) is the tangent vector of \( \gamma_1 \) at the point \( a \), and \( \gamma_2'(0) \) is the tangent vector of \( \gamma_2 \) at the point \( f(a) \) given by: \[ \frac{d}{dt} \bigg|_{t=0} \gamma_1(t) = f'(\gamma_1(0)) \cdot \gamma_1'(0) \] and similarly, the tangent vector of \( f(\gamma_2) \) at the point \( f(a) \) is \( f'(\gamma_2'(0)) = f'[\gamma_2'(0)] \). This means that the action of \( f \) multiplies the two tangent vectors \( \gamma_1'(0) \) and \( \gamma_2'(0) \) by the same nonzero complex number \( f'(a) \), and so the two tangent vectors get dilated by \( |f'(a)| \) (which does not affect their direction) and rotated by the same angle (an argument of \( f(a) \)). We end this section with yet another differentiation rule, that for inverse functions. As in the real case, this rule is only defined for functions that are bijections. ## Definition A function \( f: G \to H \) is one-to-one if for every image \( w \in H \) there is a unique \( z \in G \) such that \( f(z) = w \). The function is onto if every \( w \in H \) has a preimage \( z \in G \) that gives \( f(z) = w \). A bijection is a function that is both one-to-one and onto. If \( f: G \to H \) is a bijection then \( g: H \to G \) is the inverse of \( f \) if \( f(g(z)) = z \) for all \( z \in H \); in other words, the composition \( g \circ f \) is the identity function on \( H \). ## Proposition 12 Suppose \( G, H \subset \mathbb{C} \) are open sets, \( f: G \to H \) is a bijection, \( s: H \to G \) is the inverse function of \( f \), and \( z_0 \in H \). If \( f \) is differentiable at \( s(z_0) \) with \( f'(s(z_0)) \neq 0 \) and \( g \) is continuous at \( z_0 \), then \( g \) is differentiable at \( z_0 \), with \[ g'(z_0) = \frac{1}{f'(s(z_0))} \] ## Proof Since \( f(z_0) = z \) for all \( z \in H \), \[ g'(z_0) = \lim_{z \to f(z_0)} \frac{g(z) - g(f(z_0))}{z - f(z_0)} = \lim_{z \to f(z_0)} \frac{1}{f'(s(z_0))} \cdot \frac{g(f(z_0)) - g(z)}{g'(z_0)} \] \[ = \lim_{z \to f(z_0)} \frac{g(f(z_0)) - g(z)}{g'(z_0)(z - f(z_0))} \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 38 Context: # 2 Differentiation Now define \( z_0 = g(x_0) \) and set \[ \phi(w) = \begin{cases} \frac{f(w) - f(w_0)}{w - w_0} & \text{if } w \neq w_0 \\ f'(w_0) & \text{if } w = w_0 \end{cases} \] This is continuous at \( w_0 \) and \(\lim_{w \to w_0} \phi(w) = f'(w_0)\), so we can apply Proposition 2.6: \[ g'(x_0) = \lim_{h \to 0} \frac{1}{\phi(g(x_0 + h))} \cdot \frac{1}{f'(w_0)} \] ## 2.3 The Cauchy–Riemann Equations When considering a real-valued function \( f: \mathbb{R}^2 \to \mathbb{R} \) of two variables, there is no notion of the derivative of a function. For such a function, we instead only have partial derivatives \( \frac{\partial f}{\partial x}(x_0, y_0) \) and \( \frac{\partial f}{\partial y}(x_0, y_0) \) (and also directional derivatives) which depend on the way in which we approach a point \( (x_0, y_0) \in \mathbb{R}^2 \). For a complex-valued function \( f(z) \), we now have a new concept of the derivative \( f'(z_0) \), which definition cannot depend on the way in which we approach a point \( z_0 = (x_0, y_0) \in \mathbb{C} \). It is logical, then, that there should be a relationship between the complex derivative \( f'(z_0) \) and the partial derivatives \[ \frac{\partial f}{\partial x}(z_0) = \lim_{h \to 0} \frac{f(x_0 + h) - f(x_0, y_0)}{h} \] and \[ \frac{\partial f}{\partial y}(z_0) = \lim_{k \to 0} \frac{f(x_0, y_0 + k) - f(x_0, y_0)}{k} \] (this definition is exactly as in the real-valued case). This relationship between the complex derivative and partial derivatives is very strong, and it is a powerful computational tool. It is described by the Cauchy–Riemann equations, named after Augustin Louis Cauchy (1789–1857) and Georg Friedrich Bernhard Riemann (1826–1866), even though the equations appeared already in the works of Jean le Rond d'Alembert (1717–1783) and Leonhard Euler (1707–1783). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 41 Context: In the second case, \( \Delta z = i \Delta y \) and \[ f'(z_0) = \lim_{y_0 \to y_0} \frac{f(x_0 + i y) - f(x_0)}{i y} = \lim_{y_0 \to 0} \frac{f(x_0 + i y) - f(x_0)}{y} \] Thus, we have shown that \( f'(z_0) = f_x(z_0) - i f_y(z_0) \). (b) Suppose the Cauchy-Riemann equation (2.2) holds and the partial derivatives \( f_x \) and \( f_y \) are continuous in an open disk centered at \( z_0 \). Our goal is to prove that \( f'(z_0) = f_x(z_0) + i f_y(z_0) \). By (2.2), \[ f(z_0) = x_0 + i y_0 \quad f(z_0 + \Delta z) = f(z_0 + \Delta x + i \Delta y) \] On the other hand, we can rewrite the difference quotient for \( f'(z_0) \) as \[ f(z_0 + \Delta z) - f(z_0) = \frac{f(z_0 + \Delta z) - f(z_0)}{\Delta z} = \frac{f(z_0 + \Delta x + i \Delta y) - f(z_0)}{\Delta z} = \frac{f(z_0 + \Delta x) - f(z_0)}{\Delta z} + \frac{f(z_0 + \Delta y) - f(z_0)}{\Delta z} \] Thus, \[ \lim_{\Delta z \to 0} \frac{f(z_0 + \Delta z) - f(z_0)}{\Delta z} = \lim_{\Delta y \to 0} \frac{f(z_0 + i \Delta y) - f(z_0)}{\Delta y} = \lim_{\Delta x \to 0} \left( \frac{f(z_0 + \Delta x + i \Delta y) - f(z_0)}{\Delta z} \right). \] We claim that both limits on the right-hand side are 0, so we have achieved our set goal. The fractions \( \frac{\Delta y}{\Delta z} \) and \( \frac{\Delta x}{\Delta z} \) are bounded in absolute value by 1, so we just need to see that the differences in parentheses are 0. The second term on the right-hand side of (2.5) has a limit of 0 since, by definition, \[ f(z) = \lim_{\Delta z \to 0} \frac{f(z + \Delta z) - f(z)}{\Delta z} \] and taking the limit here as \( \Delta z \to 0 \) is the same as taking the limit as \( \Delta x \to 0 \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 42 Context: ```markdown 36 # Differentiation We cannot do something equivalent for the first term in (2.5), since now both \( \Delta x \) and \( \Delta y \) are involved, and both change as \( \Delta x \to 0 \). Instead, we apply the Mean-Value Theorem A.2 for real functions\(^1\) to the real and imaginary parts \( u(x, y) \) and \( v(x, y) \) of \( f(z) \). Theorem A.2 gives real numbers \( \xi \) and \( \eta \) such that \[ \frac{u(x_0 + \Delta x, y_0 + \Delta y) - u(x_0, y_0)}{\Delta y} = u_y(x_0, y_0 + \eta) \] and \[ \frac{v(x_0 + \Delta x, y_0 + \Delta y) - v(x_0, y_0)}{\Delta y} = v_y(x_0, y_0 + \xi). \] Thus, \[ \frac{f(x_0 + \Delta x + i \Delta y) - f(x_0 + i y)}{\Delta y} = \frac{u(x_0 + \Delta x, y_0 + \Delta y) - u(x_0, y_0)}{\Delta y} - iv_x(x_0, y_0) \] \[ = \left( \frac{u(x_0 + \Delta x, y_0 + \Delta y) - u(x_0, y_0)}{\Delta y} \right) - i v_y(x_0, y_0) + \left( \frac{u(x_0 + \Delta x, y_0 + \Delta y) - u(x_0, y_0)}{\Delta y} - iv_y(x_0, y_0) \right) = u_y(x_0, y_0) - iv_y(x_0, y_0). \tag{2.6} \] Because \( u \) and \( v \) are continuous at \( (x_0, y_0) \), \[ \lim_{\Delta y \to 0} u(x_0 + \Delta x, y_0 + \Delta y) = u(x_0, y_0) \] and \[ \lim_{\Delta y \to 0} v(x_0 + \Delta x, y_0 + \Delta y) = v(x_0, y_0), \] and so (2.6) goes to \( \Delta z \to 0 \), which we set out to prove. ## 2.4 Constant Functions As a simple application of the definition of the derivative of a complex function, we consider functions that have a derivative of 0. In a typical calculus course, one of the first applications of the Mean-Value Theorem for real-valued functions (Theorem A.1) is to constant functions. ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 43 Context: # CONSTANT FUNCTIONS ## Proposition 2.16 If \( I \) is an interval and \( f : I \rightarrow \mathbb{R} \) is a real-valued function with \( f'(x) \) defined and equal to 0 for all \( x \in I \), then there is a constant \( c \in \mathbb{R} \) such that \( f(x) = c \) for all \( x \in I \). **Proof:** The Mean-Value Theorem A.2 says that for any \( x, y \in I \), \[ f(y) - f(x) = f' \left( c \right) (y - x) \] for some \( 0 < a < 1 \). Now \( f' (x + a(y - x)) = 0 \), so the above equation yields \( f(y) = f(x) \). Since this is true for any \( x, y \in I \), the function \( f \) must be constant on \( I \). We do not (yet) have a complex version of the Mean-Value Theorem, and so we will use a different argument to prove that a complex function whose derivative is always 0 must be constant. Our proof of Proposition 2.16 required two key features of the function \( f \), both of which are somewhat obviously necessary. The first is that \( f \) be differentiable everywhere in its domain. In fact, if \( f \) is not differentiable everywhere, we can construct functions that have zero derivative almost everywhere but that have infinitely many values in their image. The second key feature is that the interval \( I \) is connected. It is certainly important for the domain to be connected in both the real and complex cases. For instance, if we define the function \[ f(z) = \begin{cases} 1 & \text{if } \text{Re}(z) \geq 0 \\ 2 & \text{if } \text{Re}(z) < 0 \end{cases} \] then \( f(z) \) is 0 for all \( z \in I \), but \( f \) is not constant. This may seem like a silly example, but it illustrates a pivotal to proving a function is constant that we must be careful of. Recall that a region of \( \mathbb{C} \) is an open connected subset. ## Theorem 2.17 If \( G \subset \mathbb{C} \) is a region and \( f : G \rightarrow \mathbb{C} \) is a complex-valued function with \( f'(z) \) defined and equal to 0 for all \( z \in G \), then \( f \) is constant. **Proof:** We will show that \( f \) is constant along horizontal segments and along vertical segments in \( G \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 45 Context: # CONSTANT FUNCTIONS ## 2.6. Proposition 2.2 is useful for showing that limits do not exist, but it is not at all useful for showing that a limit does exist. For example, define $$ f(x,y) = \frac{xy}{x^2 + y^2} \quad \text{where } (x,y) \neq (0,0). $$ Show that the limits of \( f \) along all straight lines through the origin exist and are equal, but \( \lim_{(x,y) \to (0,0)} f(x,y) \) does not exist. (Hint: Consider the limit along the parabola \( y = x^2 \).) ## 2.7. Suppose that \( f(z) = u(x,y) + iv(x,y) \) and \( u_0 = u(x_0,y_0) \) and \( v_0 = v(x_0,y_0) \). Prove that $$ \lim_{(x,y) \to (x_0,y_0)} f(z) = u_0 + iv_0 $$ if and only if $$ \lim_{(x,y) \to (x_0,y_0)} u'(x,y) = u_0 \quad \text{and} \quad \lim_{(x,y) \to (x_0,y_0)} v'(x,y) = v_0. $$ ## 2.8. Show that the function \( f : C \to \mathbb{C} \) given by \( f(z) = z^2 \) is continuous on \( C \). ## 2.9. Show that the function \( g : C \to \mathbb{C} \) given by $$ g(z) = \begin{cases} \frac{1}{z} & \text{if } z \neq 0 \\ 1 & \text{if } z = 0 \end{cases} $$ is continuous on \( C \setminus \{0\} \). ## 2.10. Determine where each of the following functions \( f : C \to C \) is continuous: (a) $$ f(z) = \begin{cases} 0 & \text{if } z = 0 \text{ or } |z| \text{ is irrational} \\ 1 & \text{if } |z| \in \mathbb{Q} \setminus \{0\} \end{cases} $$ (b) $$ f(z) = \begin{cases} 0 & \text{if } z = 0 \\ \sin z & \text{if } z \neq 0 \text{ and } z \neq re^{i\theta} \end{cases} $$ #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 48 Context: ``` 42 # Differentiation ## 2.27 Consider the general real homogeneous quadratic function \( u(x,y) = ax^2 + bxy + cy^2 \), where \( a, b, \) and \( c \) are real constants. (a) Show that \( u \) is harmonic if and only if \( a + c = 0 \). (b) If \( u \) is harmonic then show that \( u \) is the real part of a function of the form \( f(z) = A z^2 \) for some \( A \in \mathbb{C} \). Give a formula for \( A \) in terms of \( a \) and \( c \). ## 2.28 Re-prove Proposition 2.10 by using the formula for \( f' \) given in Theorem 2.13. ## 2.29 Prove that, if \( G \subset \mathbb{C} \) is a region and \( f : G \to \mathbb{C} \) is a complex-valued function with \( f''(z) \) defined and equal to 0 for all \( z \in G \), then \( f(z) = az + b \) for some \( a, b \in \mathbb{C} \). (Hint: Use Theorem 2.17 to show that \( f'(z) = a \), and then use Theorem 2.17 again for the function \( f(z) - az \).) ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 49 Context: # Chapter 3 ## Examples of Functions _To many, mathematics is a collection of theorems. For us, mathematics is a collection of examples; a theorem is a statement about a collection of examples and the purpose of proving theorems is to classify and explain the examples..._ — John B. Conway In this chapter we develop a toolkit of complex functions. Our ingredients are familiar from calculus: linear functions, exponentials and logarithms, and trigonometric functions. Yet, when we move these functions into the complex world, they take on—at times drastically different—new features. ### 3.1 Möbius Transformations The first class of functions that we will discuss in some detail are built from linear polynomials. **Definition.** A linear fractional transformation is a function of the form \[ f(z) = \frac{az + b}{cz + d} \] where \(a, b, c, d \in \mathbb{C}\) and \(ad - bc \neq 0\). Then \(f\) is called a Möbius transformation. Exercise 2.16 said that any polynomial \(p\) is an entire function, and so the linear fractional transformation \(f(z) = \frac{az + b}{cz + d}\) is holomorphic on \(\mathbb{C} \setminus \{-\frac{d}{c}\}\), unless \(c = 0\) (in which case \(c\) is entire). If \(c \neq 0\) then \(f(z) = \frac{az + b}{cz + d}\) implies \(ad - bc \neq 0\), which means that a Möbius transformation \(f(z) = \frac{az + b}{cz + d}\) will never take on the value \(-\frac{b}{d}\). Our first proposition in this chapter says that with these small observations about the domain and image of a Möbius transformation, we obtain a class of bijections, which are quite special among complex functions. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 53 Context: # INFINITY AND THE CROSS RATIO ### Example 3.6 We claim that \(\lim_{z \to \infty} f(z) = \infty\): Given \(M > 0\), let \(\delta = \frac{1}{M}\). Then \(0 < |z| < \delta\) implies \[ |f(z)| = \left| \frac{1}{z} \right| = \frac{1}{|z|} > M. \] ### Example 3.7 Let \(f(z) = \frac{az + b}{cz + d}\) be a Möbius transformation with \(c \neq 0\). Then \(\lim_{z \to \infty} f(z) = \frac{a}{c}\). To simplify the notation, introduce the constant \(L = |az - b| \geq |c| |z| - |d|.\) Given \(\epsilon > 0\), let \(N = \frac{|d|}{|a| - |c|}\). Then \(|z| > N\) implies, with the reverse triangle inequality (Corollary 1.7(b)), \[ |z + d| \geq ||c| z - |d| \geq |c| |z| - |d| \] and so \[ f(z) - \frac{a}{c} = \frac{(az + b) - \frac{a}{c}(cz + d)}{cz + d} = \frac{(ad - bc)}{c(cz + d)} \cdot L < \epsilon. \] We stress that \(\infty\) is not a number in \(\mathbb{C}\), just as \(0\) are not numbers in \(\mathbb{R}\). However, we can extend \(\mathbb{C}\) by adding on \(\infty\) if we are careful. We do so by realizing that we are always talking about a limit when handling \(\infty\). It turns out (Exercise 3.11) that the usual limit rules behave well when we mix complex numbers and zero. For example, if \(\lim_{z \to c} f(z) = L\) and \(\lim_{z \to c} g(z) = \infty\), then the usual limit of \(f(z) + g(z)\) still holds and gives \[ \lim_{z \to c} (f(z) + g(z)) = \infty. \] The following definition captures the philosophy of this paragraph. ### Definition The extended complex plane is the set \(\hat{\mathbb{C}} = \mathbb{C} \cup \{\infty\}\), together with the following algebraic properties: - (a) \(0 + \infty = \infty\) - (b) \(x + \infty = \infty\) for all \(x \in \mathbb{C}\) - (c) \(0 \cdot \infty = 0\) - (d) \(\frac{a}{0} = \infty\) - (e) if \(a \neq 0\) then \(\frac{0}{a} = 0\). The extended complex plane is also called the Riemann sphere or the complex projective line, denoted \(\text{CP}^1\). If a calculation involving \(\infty\) is not covered by the rules above then we must investigate the limit more carefully. For example, it may seem strange that \(0 + \infty\) is defined as \(\infty\). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 55 Context: We can take this remark a step further, based on the idea that three distinct points in \( \mathbb{C} \) determine a unique circle passing through them. If the three points are in \( \mathbb{C} \) and non-collinear, this fact comes straight from Euclidean geometry: if the three points are on a straight line or if one of the points is at infinity, then the circle is a straight line plus one. ### Example 3.10 The Möbius transformation \( f : \mathbb{C} \to \mathbb{C} \) given by \( f(z) = \frac{az + b}{cz + d} \) maps: - \( 1 \to 0 \) - \( i \to 1 \) - \( -1 \to \infty \) The points \( 1, i, -1 \) uniquely determine the unit circle and the points \( 0, 1, \) and \( \infty \) uniquely determine the real line, viewed as a circle in \( \mathbb{C} \). Thus Corollary 3.8 implies that if \( f \) maps the unit circle to \( \mathbb{R} \), which we already concluded in Example 3.5. Conversely, if we know where three distinct points in \( \mathbb{C} \) are transformed by a Möbius transformation, then we should be able to figure out everything about the transformation. There is a computational device that makes this easier to see. ### Definition If \( z_1, z_2, z_3 \) are any four points in \( \mathbb{C} \) with \( z_1, z_2, \) and \( z_3 \) distinct, then their cross ratio is defined as: \[ [z_1, z_2, z_3, z_4] = \frac{(z_1 - z_2)(z_3 - z_4)}{(z_1 - z_4)(z_3 - z_2)} \] This includes the implicit definitions \([z_1, z_2, z_3, \infty] = 0\) and, if one of \( z_1, z_2, \) or \( z_3 \) is \( 0 \), then the two terms containing \( 0 \) are canceled; e.g., \([0, z_2, z_3, \infty] = \frac{z_2 - z_3}{0 - z_2} = \frac{1}{-1}\). ### Example 3.11 Our running example \( f(z) = \frac{1}{z} \) can be written as \( f(z) = [1, i, -1] \). ### Proposition 3.12 The function \( f : \mathbb{C} \to \mathbb{C} \) defined by \( f(z) = [z_1, z_2, z_3, z] \) is a Möbius transformation that satisfies: \[ f(z_1) = 0, \quad f(z_2) = 1, \quad f(z_3) = \infty. \] Moreover, if any Möbius transformation with \( g(z_1) = 0, \, g(z_2) = 1, \) and \( g(z_3) = \infty \), then \( f \) and \( g \) are identical. ### Proof Most of this follows from our definition of \( f \), but we need to prove the uniqueness statement. By Proposition 3.11, the inverse \( f^{-1} \) is a Möbius transformation and, by Exercise 3.10, the composition \( g = f \circ f^{-1} \) is again a Möbius transformation. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 57 Context: # Stereographic Projection To begin, we think of \(C\) as the \((x,y)\)-plane in \(\mathbb{R}^3\), that is, \(C = \{(x,y,0) \in \mathbb{R}^3\}\). To describe stereographic projection, we will be less concerned with actual complex numbers \(x + iy\) and more concerned with their coordinates. Consider the unit sphere \[ S^2 = \{(x,y,z) \in \mathbb{R}^3 : x^2 + y^2 + z^2 = 1\}. \] The sphere and the complex plane intersect in the set \(\{(x,y,0) : x^2 + y^2 = 1\}\), which corresponds to the equator on the sphere and the unit circle on the complex plane, as depicted in Figure 3.1. Let \(N = (0,0,1)\), the north pole of \(S^2\), and let \(S = (0,0,-1)\), the south pole. ![Figure 3.1: Setting up stereographic projection.](#) ## Definition The stereographic projection of \(S^2\) to \(\hat{C}\) from \(N\) is the map \(\varphi: S^2 \setminus \{N\} \to \hat{C}\) defined as follows. For any point \(P \in S^2 \setminus \{N\}\), let \(x\) be the \(x\)-coordinate of \(P\) and let \(l\) be the line through \(N\) and \(P\). The \(z\)-coordinate of \(P\) is strictly less than \(1\), the line through \(N\) and \(P\) intersects \(C\) in exactly one point \(Q\). Define \(\varphi(P) = Q\). We also declare that \(\varphi(N) = \infty\). ## Proposition 3.14 The map \(\varphi\) is given by \[ \varphi(x,y,z) = \left( \frac{x}{1-z}, \frac{y}{1-z}, 0 \right) \quad \text{if } z \neq 1, \] \[ \varphi(x,y,z) = \infty \quad \text{if } z = 1. \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 60 Context: # Examples of Functions Project it to the plane by the stereographic projection \( \pi \), apply \( f \) to the point that results, and then pull this point back to \( S^2 \) by \( \pi^{-1} \). We know \( \varphi(x,y,z) = \left( \frac{x}{1-z}, \frac{y}{1-z} \right) \) which we now regard as the complex number \[ \rho + i \gamma = \frac{-x}{1-z} + i \frac{y}{1-z}. \] We know from a previous calculation that \( p^2 + q^2 = \frac{1}{z^2} \), which gives \( x^2 + y^2 = (1 + z)(1 - z) \). Thus, \[ f\left( \frac{x}{1-z} + i \frac{y}{1-z} \right) = \frac{1 - z}{x + iy} = \frac{1 - z}{(1 - z) x + i (1 - z) y} = \frac{1 - 2X - iY}{x^2 + y^2}. \] Rather than plug this result into the formulas for \( \pi^* \), we can just ask what triple of numbers will be mapped to this particular pair using the formulas \( \varphi(x,y,z) = \left( \frac{x}{1-z}, \frac{y}{1-z} \right) \). Thus, we have shown that the effect of \( f \) on \( S^2 \) is to take \( (x,y,z) \) to \( (x, -y, -z) \). This is a rotation around the \( x \)-axis by 180 degrees. We now have a second argument that \( f(z) \) takes circles and lines to circles and lines. A circle in \( C \) is taken to a circle on \( S^2 \) by \( \pi \). Then \( f(z) = \frac{1}{z} \) rotates the sphere which certainly takes circles to circles. Now \( g \) takes circles back to circles and lines. We can also say that the circles that go to lines under \( f(z) = \frac{1}{z} \) are the circles through 0 because 0 is mapped to \( (0, 0) \) under \( \pi \), and so a circle through 0 in \( C \) goes to a circle through the south pole on \( S^2 \). Now 180-degree rotation about the \( x \)-axis takes the south pole to the north pole, and our circle is now passing through \( N \). But we know that \( g \) will take this circle to a line in \( C \). We end by mentioning that there is, in fact, a way of putting the complex metric on \( S^2 \). It is certainly not the (finite) distance function induced by \( \pi \). Indeed, the origin in the complex plane corresponds to the south pole of \( S^2 \). We have to be able to arbitrarily far away from the origin in \( C \), so the complex distance function has to increasingly grow with the \( z \)-coordinate. The closest points are to the north pole \( N \) corresponding to 0 in \( C \), the larger their distance to the origin, and to each other! In this light, a 'line' in the Riemann sphere \( S^2 \) corresponds to a circle in \( S^2 \) through \( N \). In the regular sphere, the circle has finite lengths, but as a line on the Riemann sphere with the complex metric, it has infinite length. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 61 Context: # Exponential and Trigonometric Functions ## 3.4 Exponential and Trigonometric Functions To define the complex exponential function, we once more borrow concepts from calculus, namely the real exponential \( e^x \) and the real sine and cosine, and we finally make sense of the notation \( e^{x + iy} = e^x (\cos y + i \sin y) \). ### Definition The **complex exponential function** is defined for \( z = x + iy \) as: \[ \exp(z) = e^x (\cos y + i \sin y) = e^z. \] This definition seems a bit arbitrary. Our first justification is that all exponential rules that are used to from real numbers carry over to the complex case. They mainly follow from Proposition 1.3 and are collected in the following. ### Proposition 3.16 For all \( z_1, z_2 \in \mathbb{C} \): (a) \(\exp(z_1) \exp(z_2) = \exp(z_1 + z_2)\) (b) \(\exp(-z) = \frac{1}{\exp(z)}\) (c) \(\exp(iz) \neq 0\) (d) \(\exp(z) = \exp(\text{Re}(z))\) (e) \(\exp(z + 2\pi i) = \exp(z)\) (f) \(\exp(0) = \exp(z)\). Identity (f) is very special and has no counterpart for the real exponential function. It says that the complex exponential function is periodic with period \( 2\pi i \). This has many interesting consequences; one that may not seem too pleasant at first sight is the fact that the complex exponential function is not one-to-one. Identity (f) is not only remarkable, but we invite you to meditate on its proof below; it gives a strong indication that our definition of exp is reasonable. We also note that (f) implies that \( \exp \) is infinite. We leave the proof of Proposition 3.16 as Exercise 3.34 but give one example. ### Proof of (f) The partial derivatives of \( f(z) = \exp(z) \) are: \[ \frac{\partial f}{\partial x} = e^{x + iy} \cos y \quad \text{and} \quad \frac{\partial f}{\partial y} = e^{x + iy} (-\sin y + i \cos y). \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 62 Context: # EXAMPLES OF FUNCTIONS They are continuous in \( \mathbb{C} \) and satisfy the Cauchy–Riemann equation (2.2): \[ \frac{\partial f}{\partial x} (z) = \frac{\partial f}{\partial y} (z) \] for all \( z \in \mathbb{C} \). Thus Theorem 2.13 says that \( f(z) = \exp(z) \) is entire with derivative \[ f'(z) = \frac{\partial f}{\partial x} (z) = \exp(z). \] We should make sure that the complex exponential function specializes to the real exponential function for real arguments: indeed, if \( z = x \in \mathbb{R} \), then \[ \exp(x) = e^x = \left( \cos(0) + i\sin(0) \right) = e^x. \] The trigonometric functions—sine, cosine, tangent, cotangent, etc.—also have complex analogues; however, they do not play the same prominent role as in the real case. In fact, we can define them as merely being special combinations of the exponential function. ## Definition The (complex) sine and cosine are defined as: \[ \sin z = \frac{1}{2i} \left( \exp(iz) - \exp(-iz) \right) \] and \[ \cos z = \frac{1}{2} \left( \exp(iz) + \exp(-iz) \right), \] respectively. The tangent and cotangent are defined as: \[ \tan z = \frac{\sin z}{\cos z} = \frac{e^{iz} - e^{-iz}}{i(e^{iz} + e^{-iz}) - 1} \] and \[ \cot z = \frac{\cos z}{\sin z} = \frac{e^{iz} + 1}{e^{iz} - e^{-iz}}, \] respectively. Note that to write tangent and cotangent in terms of the exponential function, we used the fact that \( \exp(iy) - \exp(-iy) = 0 \). Because \( \exp \) is entire, so are sine and cosine. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 63 Context: # Exponential and Trigonometric Functions ![Image properties of the exponential function](path/to/image.png) Figure 3.2: Image properties of the exponential function. As with the exponential function, we should make sure that we're not redefining the real sine and cosine: if \( z \in \mathbb{R} \) then \[ \sin x = \frac{1}{2i} \left( \exp(ix) - \exp(-ix) \right) \] \[ = \frac{1}{2} \left( \cos x + i \sin x - \cos(-x) - i \sin(-x) \right) = \sin x. \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 64 Context: # Examples of Functions A similar calculation holds for the cosine. Not too surprisingly, the following properties follow mostly from Proposition 3.16. ## Proposition 3.17. For all \( z_1, z_2 \in \mathbb{C} \): \[ \begin{align*} \sin(-z) &= -\sin z & \cos(-z) &= \cos z \\ \sin(z + 2\pi) &= \sin z & \cos(z + 2\pi) &= \cos z \\ \tan(z + \pi) &= \tan z & \cot(z + \pi) &= \cot z \\ \sin(z + \frac{\pi}{2}) &= \cos z & \cos(z + \frac{\pi}{2}) &= -\sin z \\ \cos(z_1 + z_2) &= \cos z_1 \cos z_2 - \sin z_1 \sin z_2 \\ \sin(z_1 + z_2) &= \sin z_1 \cos z_2 + \cos z_1 \sin z_2 \\ \cos^2 z + \sin^2 z &= 1 & \frac{d}{dz} \sin z &= \cos z \\ \frac{d}{dz} \cos z &= -\sin z \end{align*} \] Finally, we end with caution: unlike in the real case, the complex sine and cosine are not bounded—consider, for example, \(\sin(y)\) as \(y \to \infty\). We end this section with a remark on hyperbolic trigonometric functions. The hyperbolic sine, cosine, tangent, and cotangent are defined as in the real case: ## Definition: \[ \begin{align*} \sinh z &= \frac{1}{2} \left( e^{z} - e^{-z} \right) & \cosh z &= \frac{1}{2} \left( e^{z} + e^{-z} \right) \\ \tanh z &= \frac{\sinh z}{\cosh z} = \frac{e^{z} - e^{-z}}{e^{z} + e^{-z}} & \coth z &= \frac{1}{\tanh z} = \frac{\cosh z}{\sinh z} - 1 \end{align*} \] As such, they are yet more special combinations of the exponential function. They still satisfy the identities you already know, e.g., \[ \frac{d}{dz} \sinh z = \cosh z \quad \text{and} \quad \frac{d}{dz} \cosh z = \sinh z. \] Moreover, they are related to the trigonometric functions via: \[ \sinh(iz) = i \sin z \quad \text{and} \quad \cosh(iz) = \cos z. \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 65 Context: # Logarithms and Complex Exponentials The complex logarithm is the first function we'll encounter that is of somewhat tricky nature. It is motivated as an inverse to the exponential function, that is, we're looking for a function \( \Log \) such that \[ \exp(\Log(z)) = z = \Log(\exp z). \] But because \( \exp \) is not one-to-one, this is too much to hope for. In fact, given a function \( \Log \) that satisfies the first equation, the function \( f(z) = \Log(z) + 2\pi i k \) does as well, and so there cannot be an inverse of \( \exp \) (which would have to be unique). On the other hand, \( \exp \) becomes one-to-one if we restrict its domain, so there is hope for a logarithm if we're careful about its construction and about its domain. ## Definition Given a region \( G \), any continuous function \( \Log: G \rightarrow \mathbb{C} \) that satisfies \( \exp(\Log(z)) = z \) is a branch of the logarithm (on \( G \)). To make sure this definition is not vacuous, let's write, as usual, \( z = re^{i \theta} \), and suppose that \( \Log(z) = \log |z| + i \arg(z) \). Then for the first equation to hold, we need \[ \exp(\Log(z)) = e^{\log |z| + i \arg(z)} = z, \] that is, \( e^{\log r} = r \). The latter equation is equivalent to \( r = e^{\log r} \) for some \( k \in \mathbb{Z} \), and denoting the natural logarithm of the positive real number \( r \) by \( \ln(r) \), the former equation is equivalent to \( u = \ln |z| \). A reasonable definition of a logarithm function \( \Log \) would hence be \( \Log(z) = \ln |z| + i \arg(z) \) where \( \arg(z) \) gives the argument for the complex number \( z \) according to some convention—here is an example: ## Definition Let \( \Arg \) denote the unique argument \( \theta \) of \( z \) that lies in \( (-\pi, \pi) \) (the principal argument of \( z \)). Then the principal logarithm is the function \( \Log: \mathbb{C} \setminus \{0\} \rightarrow \mathbb{C} \) defined through \[ \Log(z) = \ln |z| + i \Arg(z). \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 66 Context: Example 3.18. Here are a few evaluations of Log to illustrate this function: - Log(2) = ln(2) + Arg(2) = ln(2) - Log(-i) = ln(1) + Arg(-1) = \( \frac{3\pi}{2} \) - Log(-3) = ln(3) + Arg(-3) = ln(3) + \( \pi i \) - Log(1 - i) = ln(√2) + Arg(1 - i) = \( \frac{1}{2} \ln(2) - \frac{\pi i}{4} \) The principal logarithm is not continuous on the negative part of the real line, and so Log is a branch of the logarithm on \( \mathbb{C} \setminus \mathbb{R}^+ \). Any branch of the logarithm on a region G can be similarly extended to a function defined on \( G \setminus \{0\} \). Furthermore, the evaluation of any branch of the logarithm at a specific \( z_n \) can differ from Log(z) only by a multiple of \( 2\pi i \); the reason for this is once more the periodicity of the exponential function. So what about the second equation in (3.3), namely, Log(exp(z)) = z? Let’s try the principal logarithm: if \( z = x + iy \) then Log(exp(z)) = ln|\( z \)| + Arg(exp(z)) = ln|\( z \)| + Arg(exp(z)). The right-hand side is equal to \( z = x + iy \) if and only if \( y \in (-\pi, \pi) \). Something similar will happen with any other branch of Log of the logarithm—there will always be many z's for which Log(exp(z)) ≠ \( z \). A warning sign pointing in a similar direction concerns the much-cherished real logarithm: the ln(xy) = ln(x) + ln(y) has no analogue in \( \mathbb{C} \). For example, Log(i) + Log(-1) = \( \frac{1}{2} \ln(2 + \sqrt{2}) = \ln 2 + \frac{pi}{4} \) but Log(i - 1) = Log(-1) = \( \ln 2 - \frac{1}{2} \cdot 2 i \). The problem is that we need to come up with an argument convention to define a logarithm and then stick to this convention. There is quite a bit of subtlety here; e.g., the multi-valued map arg z := all possible arguments of z. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 67 Context: # LOGARITHMS AND COMPLEX EXPONENTIALS gives rise to a multi-valued logarithm via log z := ln |z| + i arg z. Neither arg nor log is a function, yet exp(log z) = z. We invite you to check this thoroughly; in particular, you should note how the periodicity of the exponential function takes care of the multi-valuedness of log. To end our discussion of complex logarithms on a happy note, we prove that any branch of the logarithm has the same derivative; one just has to be cautious with regions of holomorphicity. ## Proposition 3.19 If \( \text{Log}_G \) is a branch of the logarithm on G then \( \text{Log}_G \) is differentiable on G with \[ \frac{d \text{Log}_G(z)}{dz} = \frac{1}{z}. \] **Proof:** The idea is to apply Proposition 2.12 to exp and Log, but we need to be careful about the domains of these functions. Let \( H = \{ \text{Log}_G(z) : z \in G \} \), the image of Log. We apply Proposition 2.12 with \( f: H \to G \) given by \( f(z) = \text{Log}_G(z) \) and \( g: G \to H \) given by \( g(z) = \text{Log}_G(z) \); note that g is continuous, and Exercise 3.5b checks that f and g are inverses of each other. Thus Proposition 2.12 gives \[ \text{Log}_G(z) = \frac{1}{\exp(\text{Log}_G(z))} = \frac{1}{\exp(\text{Log}_G(z))} = \frac{1}{z}. \] We finish this section by defining complex exponentials. Given \( a, b \in \mathbb{C} \) with \( b \neq 0 \), the principal value of \( a^b \) is defined as \[ a^b := \exp(b \cdot \log(a)). \] Naturally, we can just as well define \( a^b \) through a different branch of the logarithm; our concern is that we use the principal value unless otherwise stated. In calculus, we can prove the equivalence of the real exponential functions as given, for \[ f(c) = e^{c}, \quad \text{where } c \in \mathbb{R}^+ \text{ and } b \text{ are defined, for example, as } c = \ln(a) + (1 + b). \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 71 Context: # LOGARITHMS AND COMPLEX EXPONENTIALS ### 3.18 Find a Möbius transformation that maps the unit disk to \(\{x + iy \in \mathbb{C} : x + y > 0\}\). ### 3.19 The Jacobian of a transformation \(z = u(x, y)\), \(w = v(x, y)\) is the determinant of the matrix \[ \begin{bmatrix} \frac{\partial u}{\partial x} & \frac{\partial u}{\partial y} \\ \frac{\partial v}{\partial x} & \frac{\partial v}{\partial y} \end{bmatrix}. \] Show that if \(f = u + iv\) is holomorphic then the Jacobian equals \(|f'(z)|^2\). ### 3.20 Find the fixed points in \(C\) of \(f(z) = \frac{az + b}{cz + d}\). ### 3.21 Find each Möbius transformation \(f\): (a) \(f\) maps \(0 \mapsto 1\), \(1 \mapsto \infty\), \(\infty \mapsto 0\). (b) \(f\) maps \(1 \mapsto -1\), \(-1 \mapsto i\), and \(i \mapsto -1\). (c) \(f\) maps the \(x\)-axis to \(y = x\), the \(y\)-axis to \(y = -x\), and the unit circle to itself. ### 3.22 (a) Find a Möbius transformation that maps the unit circle to \(\{x + iy \in \mathbb{C} : x + y = 0\}\). (b) Find two Möbius transformations that map the unit disk \[ \{z \in \mathbb{C} : |z| < 1\} \] to \(\{x + iy \in \mathbb{C} : x + y > 0\}\) and \(\{x + iy \in \mathbb{C} : x + y < 0\}\), respectively. ### 3.23 Given \(a \in \mathbb{R} \setminus \{0\}\), show that the image of the line \(y = a\) under inversion is the circle with center \(\frac{1}{a}\) and radius \(\frac{1}{|a|}\). ### 3.24 Suppose \(z_1, z_2\), and \(z_3\) are distinct points in \(\mathbb{C}\). Show that \(z\) is on the circle passing through \(z_1, z_2\), and \(z_3\) if and only if \([z, z_1, z_2, z_3]\) is real or \(\infty\). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 72 Context: # EXAMPLES OF FUNCTIONS ## 3.25 Prove that the stereographic projection of Proposition 3.14 is a bijection by verifying that \( \phi \circ \psi^{-1} \) and \( \psi \circ \phi^{-1} \) are the identity map. ## 3.26 Find the image of the following points under the stereographic projection \( \phi \): - \( (0, 0, -1) \) - \( (0, 0, 1) \) - \( (1, 0, 0) \) - \( (1, 1, 0) \) - \( (1, 1, 1) \) ## 3.27 Consider the plane \( H \) determined by \( x + y - z = 0 \). What is a unit normal vector to \( H \)? Compute the image of \( H \cap S^2 \) under the stereographic projection \( \phi \). ## 3.28 Prove that every circle in the extended complex plane \( \mathbb{C} \) is the image of some circle in \( S^2 \) under the stereographic projection \( \phi \). ## 3.29 Describe the effect of the basic Möbius transformations: rotation, real dilation, and translation on the Riemann sphere. *Hint:* For the first two, consider all circles in \( S^2 \) centered on the \( N \) axis, and all circles through both \( N \) and \( S \). For translation, consider two families of circles through \( N \), orthogonal to and perpendicular to the translation. ## 3.30 Show that \( \sin(i) = \sin(E) \) and \( \cos(i) = \cos(E) \). ## 3.31 Let \( z = x + iy \) and show that: (a) \( \sin z = \sin x \cosh y + i \cos x \sinh y \). (b) \( \cos z = \cos x \cosh y - i \sin x \sinh y \). ## 3.32 Prove that the zeros of \( \sin z \) are all real valued. Conclude that they are precisely the integer multiples of \( \pi \). ## 3.33 Describe the images of the following sets under the exponential function \( \exp(z) \): (a) The line segment defined by \( z = 1 + iy, \, 0 \leq y \leq 2\pi \) (b) The line segment defined by \( z = i + x, \, 0 \leq x \leq 2\pi \) (c) The rectangle defined by \( z = x + iy \in \mathbb{C}: \, 0 \leq x \leq 1, \, 0 \leq y \leq 2\pi \) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 73 Context: # Logarithms and Complex Exponentials ## 3.34 Prove Proposition 3.16. ## 3.35 Prove Proposition 3.17. ## 3.36 Let \( z = x + iy \) and show that (a) \( |\sin z|^2 = \sin^2 x + \sinh^2 y = \cosh^2 y - \cos^2 x \) (b) \( |\cos z|^2 = \cos^2 x + \sinh^2 y = \cosh^2 y - \sin^2 x \) (c) If \( \cos x = 0 \) then \[ | \cot z |^2 = \frac{\cosh^2 y - 1}{\sinh^2 y} \leq 1. \] (d) If \( |y| \geq 1 \) then \[ | \cot z |^2 \leq \frac{\sinh^2 y + 1}{\sinh^2 y} = 1 + \frac{1}{\sinh^2 y} \leq 2. \] ## 3.37 Show that \( \tan(i z) = i \tanh(z) \). ## 3.38 Draw a picture of the images of vertical lines under the sine function. Do the same for the tangent function. ## 3.39 Determine the image of the strip \( \{ z \in \mathbb{C} : -\frac{\pi}{2} < \Re z < \frac{\pi}{2} \} \) under the sine function. (Hint: Exercise 3.31 makes it easy to convert parametric equations for horizontal or vertical lines to parametric equations for their images. Note that the equations \( x = A \sin t \) and \( y = B \cos t \) represent an ellipse and the equations \( x = A \cosh t \) and \( y = B \sinh t \) represent a hyperbola. Start by finding the images of the boundary lines of the strip, and then find the images of a few horizontal segments and vertical lines in the strip.) ## 3.40 Find the principal values of (a) \( \log(2) \) (b) \( (-1)^i \) (c) \( \log(-1 + i) \) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 74 Context: # EXAMPLES OF FUNCTIONS ## 3.41. Convert the following expressions to the form \( z = x + iy \). (Reason carefully.) 1. \( e^z \) 2. \( e^{\cos(\log(3 + 4i))} \) 3. \( i^z \) 4. \( e^{i \pi} \) 5. \( e^{z} \) 6. \( e^{(1 + i) z} \) 7. \( \sqrt{3(1 - i)} \) 8. \( \left( \frac{1}{1} \right)^4 \) ## 3.42. Is \( \arg(E) = -\arg(z) \) true for the multiple-valued argument? What about \( \arg(E) = \Arg(z) \) for the principal branch? ## 3.43. For the multiple-valued logarithm, is there a difference between the set of all values of \( \log(z^2) \) and the set of all values of \( 2 \log(z) \)? (Hint: Try some fixed numbers for \( z \).) ## 3.44. For each of the following functions, determine all complex numbers for which the function is holomorphic. If you run into a logarithm, use the principal value unless otherwise stated. (a) \( \frac{z^2}{2} \) (b) \( \frac{1}{z^2} \) (c) \( \Log(z - 2i + 1) \) where \( \Log(z) = \ln |z| + i \arg(z) \) with \( 0 < \arg(z) < 2\pi \) (d) \( \exp(z) \) (e) \( z - 3i \) (f) \( i^z \) ## 3.45. Find all solutions to the following equations: (a) \( \Log(z) = \frac{1}{2} \) \( \cos(z) = 0 \) (b) \( \Log(z) = \frac{1}{2} \) (c) \( \exp(z) = \pi \) (d) \( \sin(z) = \cos(4) \) (e) \( \exp(z) = \exp(\sqrt{E}) \) (f) \( z = 1 + i \) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 76 Context: ``` ## 3.54 As in the previous problem, let \( f(z) = z^2 \). Let \( Q \) be the square with vertices at \( 0, 2, 2+2i, \) and \( 2i \). Draw \( f(Q) \) and identify the types of image curves corresponding to the segments from \( 2 \) to \( 2+2i \) and from \( 2+2i \) to \( 2i \). They are not parts of either straight lines or circles. **Hint:** You can write the vertical segment parametrically as \( z(t) = 2 + it \). Eliminate the parameter in \( u + iv = f(t) \) to get a \( (u, v) \) equation for the image curve. Exercises 3.53 and 3.54 are related to the cover picture of this book. ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 77 Context: # Chapter 4 ## Integration >If things are nice there is probably a good reason why they are nice; and if you do not know at least one reason for this good fortune, then you will have work to do. >— Richard Askey We are now ready to start integrating complex functions—and we will not stop doing so for the remainder of this book; it turns out that complex integration is much richer than real integration (in one variable). The initial reason for this is that we have an extra dimension to play with: the calculus integral \(\int_a^b f(z) dz\) has a fixed integration path, from \(a\) to \(b\) along the real line. For complex functions, there are many different ways to go from \(a\) to \(b\). ### 4.1 Definition and Basic Properties At first sight, complex integration is not really different from real integration. Let \(a, b \in \mathbb{R}\) and let \(C = [a, b]\) be continuous. Then we define \[ \int_C g(z) \, dz := \int_a^b \text{Re} \, g(t) \, dt + i \int_a^b \text{Im} \, g(t) \, dt. \tag{4.1} \] This definition is analogous to that of integration of a parametric curve in \(\mathbb{R}^2\). For a function that takes complex numbers as arguments, we typically integrate over a path \(γ\) (in place of a real interval). If you meditate about the substitution rule for real integrals (Theorem A.6), the following definition, which is based on (4.1), should come as no surprise. **Definition.** Suppose \(γ\) is a smooth path parametrized by \(γ(t)\), \(a \leq t \leq b\), and \(f\) is a complex function which is continuous on \(γ\). Then we define the integral of \(f\) on \(γ\) as \[ \int_γ f(z) \, dz = \int_a^b f(γ(t)) \, γ'(t) \, dt. \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 80 Context: ``` 74 # INTEGRATION For any parametrization \( \gamma(t) \), \( a \leq t \leq b \). Naturally, the length of a piecewise smooth path \( \gamma(t) \) is the sum of the lengths of its smooth components. ## Example 4.4 Let \( \gamma \) be the line segment from \( 0 \) to \( 1 + i \), which can be parametrized by \( \gamma(t) = t + it \) for \( 0 \leq t \leq 1 \). Then: \[ \text{length}(\gamma) = \int_{0}^{1} \left| 1 + i \frac{d}{dt} \right| dt = \int_{0}^{1} \sqrt{2} dt = \sqrt{2}. \] ## Example 4.5 Let \( \gamma(t) \) be the unit circle, which can be parametrized by \( \gamma(t) = e^{it} \) for \( 0 \leq t \leq 2\pi \). Then: \[ \text{length}(\gamma) = \int_{0}^{2\pi} \left| \frac{d\gamma}{dt} \right| dt = \int_{0}^{2\pi} dt = 2\pi. \] Now we observe some basic facts about how the line integral behaves with respect to function addition, scalar multiplication, inverse parametrization, and path concatenation; we also give an upper bound for the absolute value of an integral, which we will make use of time and again. ## Proposition 4.6 Suppose \( f \) is a piecewise smooth path, \( f \) and \( g \) are complex functions which are continuous on \( \gamma \) and \( \gamma \subset \mathbb{C} \). (a) \[ \int_{\gamma} (f + g) \, dz = \int_{\gamma} f \, dz + \int_{\gamma} g \, dz. \] (b) If \( \gamma \) is parametrized by \( \gamma(t) \), \( a \leq t \leq b \), we define the path \( \gamma \) from \( \gamma(a+b) \), \( a \leq t \leq b \). Then: \[ \int_{\gamma} f \, dz = \int_{\gamma} f \, dz + \int_{\gamma} g \, dz. \] (c) If \( \gamma_1 \) and \( \gamma_2 \) are piecewise smooth paths such that \( \gamma_2 \) starts where \( \gamma_1 \) ends, we define the path \( \gamma_1 \# \gamma_2 \) by following \( \gamma_1 \) to its end and then continuing on \( \gamma_2 \) to its end. Then: \[ \int_{\gamma_1 \# \gamma_2} f \, dz = \int_{\gamma_1} f \, dz + \int_{\gamma_2} f \, dz. \] (d) \[ \left| \int_{\gamma} f \, dz \right| \leq \max |f(z)| \cdot \text{length}(\gamma). \] The path \( -\gamma \) defined in (b) is the path that we obtain by traveling through \( \gamma \) in the opposite direction. ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 81 Context: # Definition and Basic Properties **Proof.** (a) follows directly from the definition of the integral and Theorem A.4, the analogous theorem from calculus. (b) follows with the real change of variables \( I = a + b - c \): \[ f = \int_{y_1}^{y_2} f(y(a + b - c)) \, dt \] \[ = -\int_{y_1}^{y_2} f(y(a + b - c)) \, dt \] \[ = \int_{y_1}^{y_2} f(y)(y(a + b - c)) \, da - \int_{y_1}^{y_2} f(y)(y) \, da = -\int f. \] (c) We need a suitable parametrization \( \gamma(t) \) for \( \gamma_1\), \( \gamma_2\). If \( \gamma_1\) has domain \([a_1, b_1]\) and \( \gamma_2\) has domain \([b_2, d_2]\), then we can use: \[ \gamma(t) = \begin{cases} \gamma_1(t) & \text{if } a_1 \leq t \leq b_1 \\ \gamma_2(t - b_1 + a_2) & \text{if } b_1 < t \leq b_2 - a_2 \end{cases} \] with domain \([a_1, b_1, b_2 - a_2]\). Now we break the integral over \( \gamma_2\) into two pieces and apply the change of variables \( I = e - b_1 + a_2\): \[ \int_{\gamma_2} f = \int_{a_1}^{b_1} f(y(t)) \, dt \] \[ = \int_{a_1}^{b_1} f(y(t)) \, dt + \int_{b_1}^{b_2} f(y(t)) \, dt. \] \[ = \int f + \int f. \] The last step follows since \( y\) restricted to \([a_1, b_1]\) is \( \gamma\) and \( y\) restricted to \([b_1 + b_2 - a_2]\) is a reparametrization of \( \gamma_2\). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 83 Context: # ANTIDERIVATIVES ## Example 4.8 We have already seen that \( F(z) = z^2 \) is entire and has derivative \( f(z) = 2z \). Thus, \( F \) is an antiderivative of \( f \) on any region \( G \subseteq \mathbb{C} \). The same goes for \( F(z) = z^2 + C \), where \( C \in \mathbb{C} \) is any constant. ## Example 4.9 Since \[ \frac{d}{dx} \left( \frac{1}{2} ( \exp(i z) - \exp(-i z) ) \right) = \frac{1}{2} (\exp(i z) + \exp(-i z)), \] we have \[ F(z) = \sin z \] is an antiderivative of \( f(z) = \cos z \) on \( \mathbb{C} \). ## Example 4.10 The function \( F(z) = \log z \) is an antiderivative of \( f(z) = \frac{1}{z} \) on \( \mathbb{C} \setminus \{0\} \). Note that \( f \) is holomorphic in the larger region \( \mathbb{C} \setminus \{0\} \); however, we will see in Example 4.14 that \( f \) cannot have an antiderivative on that region. Here is the complex analogue of Theorem A.3(b). ## Theorem 4.11 Suppose \( G \subseteq \mathbb{C} \) is a region and \( \gamma \subseteq G \) is a piecewise smooth path with parametrization \( \gamma(t), \quad a \leq t \leq b \). If \( f \) is continuous on \( G \) and \( F \) is any antiderivative of \( f \) on \( G \) then \[ \int_{\gamma} f = F(\gamma(b)) - F(\gamma(a)). \] **Proof.** This follows immediately from the definition of a complex integral and Theorem A.3(b), since \( F'(\gamma(t)) = f(\gamma(t)) \). \[ \int_{\gamma} f = \int_a^b F'(\gamma(t)) \gamma'(t) \, dt = F(\gamma(b)) - F(\gamma(a)). \] ## Example 4.12 Since \( F(z) = \frac{1}{2} z^2 \) is an antiderivative of \( f(z) = z \) in \( \mathbb{C} \), \[ \int_{\gamma} f = \int_a^b \left( \frac{1}{2} (t^2) - \frac{1}{2} (a^2) \right) = \frac{1}{2} z^2 \] for each of the three paths in Example 4.11. There are several interesting consequences of Theorem 4.11. For starters, if \( \gamma \) is closed (that is, \( \gamma(a) = \gamma(b) \)), we effortlessly obtain the following. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 89 Context: ```markdown # CAUCHY'S THEOREM For \( 0 \leq s \leq 1 \), let \( \gamma \) be the path parametrized by \( h(t, s) \), \( 0 \leq t \leq 1 \). Consider the function \( I : [0, 1] \to \mathbb{C} \) given by \[ I(s) := \int_{\gamma} f. \] Thus, \( I(0) = \int_{\gamma(0)} f \) and \( I(1) = \int_{\gamma(1)} f \). We will show that \( I \) is constant; in particular, \( I(0) = I(1) \), which proves the theorem. By Leibniz rule (Theorem A.9), \[ \frac{d}{ds} I(s) = \int_{\gamma(h(t,s))} f \frac{\partial h}{\partial s} \, dt = \int_{0}^{1} f\left(h(t, s)\right) \frac{\partial h(t, s)}{\partial s} \, dt \] \[ = \int_{0}^{1} \left( f\left(h(t,s)\right) \frac{\partial h(t,s)}{\partial s}\right) \, dt. \] Note that we used Theorem A.7 to switch the order of the second partials in the penultimate step—here is where we need our assumption that \( h \) has continuous second partials. Also, we needed continuity of \( f \) in order to apply Leibniz's rule. If \( b \) is piecewise defined, we split up the integral accordingly. Finally, by the Fundamental Theorem of Calculus (Theorem A.3), applied separately to the real and imaginary parts of the above integral, \[ \frac{d}{ds} I(s) = \int_{\gamma(h(t, s))} f \frac{\partial h}{\partial s} \, dt = f\left(h(t,s)\right) \bigg|_{t=0}^{t=1} = f(h(1,s)) - f(h(0,s)) \frac{\partial h}{\partial s} = 0, \] where the last step follows from \( h(0,s) = h(1,s) \) for all \( s \). **Definition.** Let \( G \subset \mathbb{C} \) be a region. If the closed path \( \gamma \) is \( G \)-homotopic to a point (that is, a constant path) then it is \( G \)-contractible, and we write \( \gamma \simeq_G \). (See Figure 4.2 for an example.) The fact that an integral over a point is zero has the following immediate consequence. ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 91 Context: Example 4.23. We'd like to compute \[ \int_{C} \frac{dz}{z^2 - 2z} \] where \(C\) is the unit circle, oriented counter-clockwise. (Try computing it from first principles.) We use a partial fractions expansion to write \[ \int_{C} \frac{dz}{z^2 - 2z} = \frac{1}{2} \int_{C} \frac{dz}{z - 2} - \frac{1}{2} \int_{C} \frac{dz}{z}. \] The first integral on the right-hand side is zero by Corollary 4.20 applied to the function \(f(z) = \frac{1}{z}\) (note that \(f\) is holomorphic in \(C \setminus \{2\}\) and \(C\) is \((C \setminus \{2\})\)-contractible). The second integral is \(2\pi i\) by Exercise 4.4, and so \[ \int_{C} \frac{dz}{z^2 - 2z} = -\pi i. \] Sometimes Corollary 4.20 itself is known as Cauchy's Theorem. See Exercise 4.26 for a related formulation of Corollary 4.20, with a proof based on Green's Theorem. ### 4.4 Cauchy's Integral Formula We recall our notations: - \(C(r) = \{ z \in \mathbb{C} : |z - a| = r \}\) - \(D(r) = \{ z \in \mathbb{C} : |z - a| < r \}\) - \(D[-r] = \{ z \in \mathbb{C} : |z - a| \leq r \}\) Theorem 4.24. If \(f\) is holomorphic in an open set containing \(D[r]\) then \[ f(w) = \frac{1}{2\pi i} \int_{C(r)} f(z) \frac{dz}{z - w}. \] This is Cauchy's Integral Formula for the case that the integration path is a circle; we will prove the general statement at the end of this chapter. However, already this special case is worth meditating over: the data on the right-hand side of Theorem 4.24 #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 105 Context: # VARIATIONS OF A THEME Theorem 5.1 has several important consequences. For starters, it can be used to compute certain integrals. ## Example 5.2 \[ \int_{C(0,1)} \frac{\sin(z)}{z^2} \, dz = \frac{2\pi i}{2\pi} \left. \frac{d}{dx} \sin(z) \right|_{z=0} = 2\pi i \cos(0) = 2\pi i. \] ![Figure 5.1: The integration paths in Example 5.3.](path/to/figure5.1.png) ## Example 5.3 To compute the integral \[ \int_{C(0,2)} \frac{dz}{z^2(z-1)}, \] we could employ a partial fractions expansion similar to the one in Example 4.23, or moving the integration path similar to the one in Exercise 4.29. To exhibit an alternative, we split up the integration path as illustrated in Figure 5.1: we introduce an additional path that separates 0 and 1. If we integrate on these two new closed paths (\(Y_1\) and \(Y_2\)) counterclockwise, the two contributions along the new path will cancel each other. The effect is that we transformed an integral for which two singularities were inside the integration path into a sum of two integrals, each of which has only one singularity inside the integration path; these new integrals will... #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 109 Context: ```markdown # Taking Cauchy’s Formulas to the Limit ## Proof Suppose (by way of contradiction) that \( p(z) \) does not have any roots, that is, \( p(z) \neq 0 \) for all \( z \in \mathbb{C} \). Then \( \frac{1}{p(z)} \) is entire, and so Cauchy’s Integral Formula (Theorem 4.24) gives \[ \frac{1}{p(0)} = \frac{1}{2\pi i} \int_{\mathcal{C}(0, R)} \frac{p'(z)}{p(z)} \, dz, \quad \text{for any } R > 0. \] Let \( d \) be the degree of \( p(z) \) and \( a_k \) its leading coefficient. Propositions 4.6(d) and 5.10 allow us to estimate, for sufficiently large \( R \): \[ \left| \frac{1}{p(0)} \right| = \frac{1}{2\pi} \int_{\mathcal{C}(0, R)} \frac{1}{|p(z)|} \, |dz| \leq \frac{1}{2\pi} \cdot \frac{1}{\text{ext } |a_k| R^{d}} \cdot |2\pi R| = \frac{2 |a_k|}{R^{d}}. \] The left-hand side is independent of \( R \), while the right-hand side can be made arbitrarily small (by choosing \( R \) sufficiently large), and so we conclude that \( \frac{1}{p(0)} = 0 \), which is impossible. ## Theorem 5.11 Theorem 5.11 implies that any polynomial \( p \) can be factored into linear terms of the form \( z - a \) where \( a \) is a root of \( p \) as we can apply the corollary, after getting a root to \( z^n = 0 \) (which is again a polynomial by the division algorithm), etc. (see also Exercise 5.11). A compact reformulation of the Fundamental Theorem of Algebra (Theorem 5.11) is to say that \( \mathbb{C} \) is algebraically closed in contrast, \( \mathbb{R} \) is not algebraically closed. ### Example 5.12 The polynomial \( p(z) = z^4 + 5z^2 + 3 \) has no roots in \( \mathbb{R} \). The Fundamental Theorem of Algebra (Theorem 5.11) states that \( p \) must have a root (in fact, four roots) in \( \mathbb{C} \): \[ p(z) = (z^2 + 1)(z^2 + 3) = (z + i)(z - i)(\sqrt{3} + z)(\sqrt{3} - z) \quad \Box \] Another powerful consequence of Theorem 5.1 is the following result, which again has no counterpart in real analysis (consider, for example, the ratio test). ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 110 Context: # Corollary 5.13 (Liouville's Theorem) Any bounded entire function is constant. ## Proof: Suppose \( |f(z)| \leq M \) for all \( z \in \mathbb{C} \). Given any \( \epsilon > 0 \), we apply Theorem 5.1 with the circle \( C(R) \); note that we can choose any \( R > 0 \) because \( f \) is entire. By Proposition 4.16(1), \[ \left| \frac{f(w)}{2\pi i \int_{C(R)} (z - w)^{-1} dz} \right| = \frac{1}{2\pi i} \int_{C(R)} \frac{f(z)}{(z - w)^2} dz \leq \frac{1}{2\pi} \max_{z \in C(R)} |f(z)| \cdot \frac{1}{2\pi R}. \] The right-hand side can be made arbitrarily small, as we are allowed to choose \( R \) as large as we want. This implies that \( f' = 0 \), and hence, by Theorem 2.17, \( f \) is constant. As an example of the usefulness of Liouville's theorem (Corollary 5.13), we give another proof of the Fundamental Theorem of Algebra, close to Gauss's original proof. ## Second proof of Theorem 5.11 (Fundamental Theorem of Algebra): Suppose (by way of contradiction) that \( f \) does not have any roots, that is, \( f(z) \neq 0 \) for all \( z \in \mathbb{C} \). Then the function \( f(z) = \frac{1}{f(z)} \) is entire. But \( f \to 0 \) as \( |z| \to \infty \), by Proposition 5.10; consequently, by Exercise 5.10, \( f \) is bounded. Now we apply Corollary 5.13 to deduce that \( f \) is constant. Hence \( f \) is constant, which contradicts our assumptions. As one more example of the theme of getting results from Cauchy's Integral Formulas by taking the limit as a path “goes to infinity,” we compute an improper integral. ## Example 5.14: We will compute the (real) integral \[ \int_0^{\infty} \frac{dx}{x^2 + 1} = \pi. \] Let \( C_R \) be the counterclockwise semicircle formed by the segment \([-R, R]\) of the real axis from \(-R\) to \(R\), followed by the circular arc \( \gamma_R \) of radius \( R \) in the upper half plane from \( R \to -R \), see Figure 5.2. > *This theorem (the historical reason commonly attributed to Joseph Liouville (1809–1883). It was published earlier by Cauchy in fact, Gauss may well have known about it before Cauchy.)* #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 112 Context: # Exercises ## 5.1 Compute the following integrals, where \(\square\) is the boundary of the square with vertices at \(\pm 4i\), positively oriented: (a) \(\int_{\square} \frac{e^{z^2}}{z^2} \, dz\) (b) \(\int_{\square} \frac{z^3}{(x - \pi^2)} \, dz\) (c) \(\int_{\square} \frac{\sin(2z)}{(z - \pi)^2} \, dz\) (d) \(\int_{\square} \frac{e^{z} \cos(z)}{(x - \pi)} \, dz\) ## 5.2 Prove the formula for \(f^{(n)}\) in Theorem 5.1. *Hint: Modify the proof of the integral formula for \(f^{(n)}(w)\) as follows:* (a) Write a difference quotient for \(f^{(n)}(w)\), and use the formula for \(f^{(n)}(w)\) in Theorem 5.1 to convert this difference quotient into an integral of \(f(z)\) divided by some polynomial. (b) Subtract the desired integral formula for \(f^{(n)}\) from your integral for the difference quotient, and simplify to get the analogue of (5.1). (c) Find a bound as in the proof of Theorem 5.1 for the integrand, and conclude that the limit of the difference quotient is the desired integral formula. ## 5.3 Integrate the following functions over the circle \(C(0,3)\): (a) \(\log(z - 4i)\) (b) \(\frac{1}{z - \frac{1}{2}}\) (c) \(\frac{1}{z^2}\) (d) \(\frac{e^{z}}{z^3}\) (e) \(\cos(z) \, z\) (f) \(z^{-3}\) (g) \(\frac{\sin(z)}{(z^2 + 1)}\) (h) \(\frac{1}{(4 + z^2 + 1)}\) (i) \(\frac{e^{2z}}{(z - 1)(\sqrt{z - 2})}\) ## 5.4 Compute \(\int_{C(2)} \frac{e^{z}}{(z - w)^2}\, dz\) where \(w\) is any fixed complex number with \(|w| \neq 2\). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 113 Context: 5.5. Define \( f : [0, 1] \to \mathbb{C} \) through \[ f(x) := \int_0^1 \frac{dw}{1 - wx} \] (the integration path is from 0 to 1 along the real line). Prove that \( f \) is holomorphic in the unit disk \( D(0, 1) \). 5.6. To appreciate Corollary 5.5, show that the function \( f : \mathbb{R} \to \mathbb{R} \) given by \[ f(x) = \begin{cases} x^2 \sin\left(\frac{1}{x}\right) & \text{if } x \neq 0 \\ 0 & \text{if } x = 0 \end{cases} \] is differentiable in \( \mathbb{R} \), yet \( f' \) is not even continuous (much less differentiable) at 0. 5.7. Prove that \( f(2) = e^2 \) does not have an antiderivative in any nonempty region. 5.8. Show that \( \exp(\sin z) \) has an antiderivative on \( \mathbb{C} \). (What is it?) 5.9. Find a region on which \( f(z) = \exp(z^2) \) has an antiderivative. (Your region should be as large as you can make it. How does this compare with the real function \( f(x) = e^x \)?) 5.10. Suppose \( f \) is continuous on \( \mathbb{C} \) and \( \lim_{z \to \infty} f(z) = L \). Show that \( f \) is bounded. (Hint: If \( \lim_{z \to \infty} f(z) = L \), use the definition of the limit at infinity to show that there is \( R > 0 \) so that \( |f(z) - L| < \epsilon \) if \( |z| > R \). Now argue that \( |f(z)| < |L| + 1 \) for \( |z| \geq R \). Use an argument from calculus to show that \( |f(z)| \) is bounded for \( |z| \leq R \).) 5.11. Let \( p(z) \) be a polynomial of degree \( n > 0 \). Prove that there exist complex numbers \( c_1, c_2, \ldots, c_n \), and positive integers \( j_1, \ldots, j_n \) such that \[ p(z) = c e^{-j_1} (z - z_1)^{j_1} \cdots (z - z_n)^{j_n} \] where \( j_1 + \ldots + j_n = n \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 115 Context: # Taking Cauchy's Formulas to the Limit ## 5.20. Compute \[ \int_{-\infty}^{\infty} \frac{\cos(x)}{x^2+1} \, dx. \] ## 5.21. This exercise outlines how to extend some of the results of this chapter to the Riemann sphere as defined in Section 3.2. Suppose \( G \subset \mathbb{C} \) is a region that contains 0, let \( f \) be a continuous function on \( G \), and let \( \gamma \subset G \) be a piecewise smooth path in \( G \) avoiding the origin, parametrized as \( \gamma(t) \), for \( a \leq t \leq b \). ### (a) Show that \[ \int_{\gamma} f(z) \, dz = \int_{a}^{b} \frac{f(\gamma(t))}{\gamma'(t)} \, dt \] where \( o(t) = \gamma(t) \), \( a \leq t \leq b \). Now suppose \(\mathrm{Im}(f) = \{ f(z) \} \) is finite. Let \( H = \{ z \in G \setminus \{ 0 \} \} \) and define the function \( g : H \cup \{ 0 \} \to \mathbb{C} \) by \[ g(z) = \begin{cases} \frac{f(z)}{L} & \text{if } z \in H, \\ 0 & \text{if } z = 0. \end{cases} \] Thus \( g \) is continuous on \( H \cup \{ 0 \} \) and gives the identity \[ \int_{H} f \, dz = \int g. \] In particular, we can transfer certain properties between these two integrals. For example, if \( f \) is path independent, so is \( g \). Here is but one application: ### (a) Show that \[ \int_{\gamma} f(z) \, dz \text{ is path independent for any integer } n \neq -1. \] ### (b) Conclude (once more) that \[ \int z^n \, dz = 0 \text{ for any integer } n \neq -1. \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 116 Context: # Chapter 6 ## Harmonic Functions The shortest route between two truths in the real domain passes through the complex domain. Jacques Hadamard (1865–1963) We will now spend a short while on certain functions defined on subsets of the complex plane that are real valued, namely those functions that are harmonic in some region. The main motivation for studying harmonic functions is that the partial differential equation they satisfy is very common in the physical sciences. Their definition briefly showed its face in Chapter 2, but we study them only now in more detail, since we have more machinery at our disposal. This machinery comes from complex-valued functions, which are, nevertheless, intimately connected to harmonic functions. ### 6.1 Definition and Basic Properties Recall from Section 2.3 the definition of a harmonic function: **Definition.** Let \( G \subset \mathbb{C} \) be a region. A function \( u : G \rightarrow \mathbb{R} \) is harmonic in \( G \) if it has continuous second partials in \( G \) and satisfies the Laplace* equation \[ u_{xx} + u_{yy} = 0. \] **Example 6.1.** The function \( u(x, y) = xy \) is harmonic in \( C \) since \( u_{xx} + u_{yy} = 0 + 0 = 0. \) **Example 6.2.** The function \( u(x, y) = e^x \cos(y) \) is harmonic in \( C \) because \[ u_{xx} + u_{yy} = e^x \cos(y) - e^x \cos(y) = 0. \] 1. Named after Pierre-Simon Laplace (1749–1827). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 118 Context: # HARMONIC FUNCTIONS ## Theorem 6.6. Suppose \( u \) is harmonic on a simply-connected region \( G \). Then there exists a harmonic function \( v \) in \( G \) such that \( f = u + iv \) is holomorphic in \( G \). The function \( v \) is called a **harmonic conjugate of** \( u \). **Proof:** We will explicitly construct a holomorphic function \( f \) (and thus \( v = \text{Im } f \)). First, let \[ g = u_x - i u_y. \] The plan is to prove that \( g \) is holomorphic, and then to construct an antiderivative of \( g \), which will be almost the function \( f \) that we are after. To prove that \( g \) is holomorphic, we use Theorem 2.13: first because \( u \) is harmonic, \( \text{Re } g = u_x \) and \( \text{Im } g = -u_y \) have continuous partials. Moreover, again because \( u \) is harmonic, \( \text{Re } g \) and \( \text{Im } g \) satisfy the Cauchy-Riemann equations (2.3): \[ \begin{align*} \text{(Re } g)_y & = u_{xy} = -u_{yx} = -(\text{Im } g)_x, \\ \text{(Re } g)_x & = u_{xx} = -u_{yy} = -(\text{Im } g)_y. \end{align*} \] Theorem 2.13 implies that \( g \) is holomorphic in \( G \), and so we can use Corollary 5.8 to obtain an antiderivative \( f \) of \( g \) (here is where we use the fact that \( G \) is simply connected). Now we decompose \( g \) into its real and imaginary parts as \( h = a + ib \). Then, again using Theorem 2.13, \[ g = b' - a' i, \] (The second equation follows from the Cauchy-Riemann equations (2.3)). But the real part of \( g \) is \( g_x = a \), and thus \( u_x = a = \text{Re } f \) for some function \( f \) that depends only on \( y \). On the other hand, comparing the imaginary parts of \( g' \) yields \( -u_y = -a' = b_y = \text{Im } f \) where \( c \) depends only on \( y \). Hence \( f \) has the form \[ f(x) = h(x) + c \] is a function holomorphic in \( G \) whose real part is \( u \), as promised. > As a side remark, with hindsight it should not be surprising that the function \( g \) that we first constructed in our proof is the derivative of the sought-after function. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 121 Context: Theorem 6.10. Suppose \( u \) is harmonic in the region \( G \) and \( \overline{D(u, r)} \subset G \). Then \[ u(x) = \frac{1}{2\pi} \int_{D(u,r)} u(y + r e^{i\theta}) d\theta. \] **Proof.** Exercise 6.14 provides \( x \in D(u,r) \subset D[u,r] \subset G \). The open disk \( D[u,r] \) is simply connected, so by Theorem 6.6 there is a function \( f \) holomorphic in \( D[u,r] \) such that \( u = \operatorname{Re} f \) on \( D[u,r] \). Now we apply Corollary 4.25 to \( f \): \[ f(x) = \frac{1}{2\pi} \int_{0}^{2\pi} f(x + r e^{i\theta}) d\theta. \] Theorem 6.10 follows by taking the real part on both sides. **Corollary** 4.25 and Theorem 6.10 say that holomorphic and harmonic functions have the mean-value property. Our next result is an important consequence of this property to extreme values of a function. **Definition.** Let \( G \) be a region. The function \( u : G \to \mathbb{R} \) has a strong relative maximum at \( x_0 \in G \) if there exists a disk \( D[u, r] \subset G \) such that \( u(x) \leq u(x_0) \) for all \( x \in D[u, r] \) and \( u(x_0) < u(x) \) for some \( y \in D[u, r] \). The definition of a strong relative minimum is analogous. Theorem 6.11. If \( u \) is harmonic in the region \( G \), then it does not have a strong relative maximum or minimum in \( G \). **Proof.** Assume, by way of contradiction, that \( u \) has a strong relative maximum. Then there is a disk in \( G \) centered at \( x_0 \) containing a point \( x \) with \( u(x) < u(x_0) \). Let \( r = |x - x_0| \) and apply Theorem 6.10: \[ u(x) = \frac{1}{2\pi} \int_{0}^{2\pi} u(x_0 + r e^{i\theta}) d\theta. \] Intuitively, this cannot hold, because some of the function values we're integrating are smaller than \( u(x_0) \), contradicting the mean-value property. To make this into a thorough argument, suppose that \( u(x) < u(x_0) \) for \( r \leq 5 \) and \( x \in [0, 2r] \). Now we split up the mean-value... #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 124 Context: where \( P_\nu(r) \) is the Poisson kernel which we introduced in Exercise 4.31. Then \( u \) is the desired extension: it is continuous on the closed unit disk, harmonic in the open unit disk, and agrees with \( u \) on the unit circle. In simple cases this solution can be converted to solutions in other regions, using a conformal map to the unit disk. All of this is beyond the scope of this book, though Exercise 6.13 gives some indication why the above formula does the trick. At any rate, we remark that Corollary 6.14 says that the solution to the Dirichlet problem is unique. ## Exercises 6.1. Show that all partial derivatives of a harmonic function are harmonic. 6.2. Suppose \( u(x, y) \) and \( v(x, y) \) are harmonic in \( G \), and \( \varepsilon \in \mathbb{R} \). Prove that \( u(x, y) + \varepsilon v(x, y) \) is also harmonic in \( G \). 6.3. Give an example that shows that the product of two harmonic functions is not necessarily harmonic. 6.4. Let \( u(x, y) = e^y \sin y \). (a) Show that \( u \) is harmonic on \( \mathbb{C} \). (b) Find an entire function \( f \) such that \( \text{Re}(f) = u \). 6.5. Consider \( u(x, y) = \ln(x^2 + y^2) \). (a) Show that \( u \) is harmonic on \( \mathbb{C} \setminus \{(0, 0)\} \). (b) Prove that \( u \) is not the real part of a function that is holomorphic in \( \mathbb{C} \setminus \{(0, 0)\} \). 6.6. Show that if \( f \) is holomorphic and nonzero in \( G \), then \( \ln|f(x, y)| \) is harmonic in \( G \). 6.7. Suppose \( u(x, y) \) is a function \( \mathbb{R}^2 \rightarrow \mathbb{R} \) that depends only on \( x \). When is \( u \) harmonic? #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 126 Context: # Harmonic Functions (a) Recall the Möbius function \[ f(z) = \frac{z - a}{1 - \overline{a}z}, \] for some fixed \( a \in \mathbb{C} \) with \( |a| < 1 \), from Exercise 3.9. Show that \( u(f(z)) \) is harmonic on an open disk \( D[0, R] \) containing \( D(0, 1) \). (b) Apply Theorem 6.10 to the function \( u(f(z)) \) with \( v = 0 \) to deduce \[ u(a) = \frac{1}{2\pi} \int_{C(a)} \frac{u(f(z))}{z} dz. \] (c) Recalling, again from Exercise 3.9, that \( f(z) \) maps the unit circle to itself, apply a change of variables to (6.3) to prove \[ u(a) = \frac{1}{2\pi} \int_{0}^{2\pi} u(e^{i\theta}) \left| 1 - \frac{|a|^2}{|e^{i\theta} - a|^2} \right| d\theta. \] (d) Deduce (6.2) by setting \( a = re^{i\theta} \). ## Exercise 6.14 Suppose \( G \) is open and \( \overline{D(a, r)} \subset G \). Show that there is \( R > r \) so that \( \overline{D(a, r)} \subset D[R] \subset G \). (Hint: If \( G = \mathbb{C} \) just take \( R = r + 1 \). Otherwise choose some \( w \in G \), let \( M = |w - a| \), and let \( K = \overline{D(a, M)} \subset G \). Show that \( K \) is nonempty, closed, and bounded, and apply Theorem A1 to find a point \( x_0 \in K \) that minimizes \( f(z) = |z - a| \) on \( K \). Show that \( R = |x_0 - a| \) works.) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 127 Context: # Chapter 7 ## Power Series *It is a pain to think about convergence but sometimes you really have to.* **Sinai Robbins** Looking back to what machinery we have established so far for integrating complex functions, there are several useful theorems we developed in Chapters 4 and 5. But there are some simple-looking integrals, such as: \[ \int_{C} \frac{\exp(z)}{\sin(z)} \, dz, \tag{7.1} \] that we cannot compute with this machinery. The problems, naturally, come from the singularities at \(0\) and \(x\) inside the integration path, which in turn stem from the roots of the sine function. We might try to simplify this problem a bit by writing the integral as the sum of integrals over the two "D" shaped paths shown in Figure 5.1. ![Figure 7.1: Modifying the integration path for (7.1).](path/to/figure5.1) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 128 Context: # 122 Power Series (the integrals along the common straight line segments cancel). Furthermore, by Cauchy’s Theorem 4.18, we may replace these integrals with integrals over small circles around \(a\) and \(b\). This transforms (7.1) into a sum of two integrals, which we are no closer to being able to compute; however, we have localized the problem, in the sense that we now “only” have to compute integrals around one of the singularities of our integral. This motivates developing techniques to approximate complex functions locally, in analogy with the development of Taylor series in calculus. It is clear that we need to go further here, as we’d like to have such approximations near a singularity of a function. At any rate, to get any of this started, we need to talk about sequences and series of complex numbers and functions, and this chapter develops them. ## 7.1 Sequences and Completeness As in the real case, a \( (complex) \) sequence is a function from the positive (sometimes the nonnegative) integers to the complex numbers. Its values are usually written as \( a_n \) (as opposed to \( a(n) \)) and we commonly denote the sequence by \( (a_n)_{n=1}^{\infty} \) or simply \( (a_n) \). Considering such a sequence as a function of \( n \), the notion of convergence is merely a repeat of the definition we gave in Section 3.2, adjusted to the fact that \( n \) is an integer. **Definition.** Suppose \( (a_n) \) is a sequence and \( L \in \mathbb{C} \) such that for all \( \epsilon > 0 \) there is an integer \( N \) such that for all \( n \in \mathbb{N} \), we have \( |a_n - L| < \epsilon \). Then the sequence \( (a_n) \) is convergent and \( L \) is its limit; in symbols we write \[ \lim_{n \to \infty} a_n = L. \] If no such \( L \) exists then the sequence \( (a_n) \) is divergent. As in our previous definitions of limit, the limit of a sequence is unique if it exists. See Exercise 7.7. ### Example 7.1 We claim that \[ \lim_{n \to \infty} \frac{1}{n} = 0: \text{ Given } \epsilon > 0, \text{ choose } N > \frac{1}{\epsilon}. \] Then for any \( n \geq N \), \[ \left| \frac{1}{n} - 0 \right| = \frac{1}{n} \leq \frac{1}{N} < \epsilon. \] \(\blacksquare\) *There will be no surprises in this chapter of the nature real series converges.* #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 129 Context: To prove that a sequence \((a_n)\) is divergent, we have to show the negation of the statement that defines convergence; that is, given any \(L \in \mathbb{C}\), there exists \(\epsilon > 0\) such that, given any integer \(N\), there exists an integer \(n > N\) such that \(|a_n - L| > \epsilon\). (If you have not negated any mathematical statements, this is worth meditating about.) ### Example 2.7: The sequence \((a_n = i^n)\) diverges: Given \(L \in \mathbb{C}\), choose \(L = \frac{1}{2}\). We consider two cases: If \(\text{Re}(L) > 0\), then for any \(N\), choose \(n > N\) such that \(a_n = -1\). (This is always possible since \(a_{2k} = i^{2k} = -1\) for any \(k \geq 0\).) Then \[ |a_n - L| = |1 + L| > \frac{1}{2}. \] If \(\text{Re}(L) < 0\), then for any \(N\), choose \(n > N\) such that \(a_n = 1\). (This is always possible since \(a_{4k} = i^{4k} = 1\) for any \(k \geq 0\).) Then \[ |a_n - L| = |1 - L| > \frac{1}{2}. \] This proves that \((a_n = i^n)\) diverges. The following limit laws are the cousins of the identities in Propositions 2.4 and 2.6, with one little twist. ### Proposition 7.3. Let \((a_k)\) and \((b_k)\) be convergent sequences and \(c \in \mathbb{C}\). Then 1. \(\lim_{k \to \infty} (a_k + b_k) = \lim_{k \to \infty} a_k + \lim_{k \to \infty} b_k.\) 2. \(\lim_{k \to \infty} (a_k - b_k) = \lim_{k \to \infty} a_k - \lim_{k \to \infty} b_k.\) 3. \(\lim_{k \to \infty} (c a_k) = c \cdot \lim_{k \to \infty} a_k.\) 4. \(\lim_{k \to \infty} (a_k b_k) = \lim_{k \to \infty} a_k \cdot \lim_{k \to \infty} b_k.\) 5. \(\lim_{k \to \infty} \frac{a_k}{b_k} = \frac{\lim_{k \to \infty} a_k}{\lim_{k \to \infty} b_k}\) where \(b_k \neq 0\) for all sufficiently large \(k\), assuming \(\lim_{k \to \infty} b_k \neq 0.\) 6. \(\lim_{k \to \infty} k = \infty.\) Again, the proof of this proposition is essentially a repeat from arguments we have given in Chapters 2 and 3, as you should convince yourself in Exercise 7.4. We will assume, as an axiom, that it is complete. To phrase this precisely, we need the following. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 130 Context: # POWER SERIES ## Definition The sequence \((a_n)\) is monotonic if it is either nondecreasing \((a_n \geq a_{n-1}\) for all \(n)\) or nonincreasing \((a_n \leq a_{n-1}\) for all \(n)\). There are many equivalent ways of formulating the completeness property for the reals. Here is what we'll go by: ## Axiom (Monotone Sequence Property) Any bounded monotonic sequence converges. This axiom (or one of its many equivalent statements) gives arguably the most important property of the real number system: namely, that we can, in many cases, determine that a given sequence converges without knowing the value of the limit. In this sense we can use the sequence to define a real number. ## Example 7.4 Consider the sequence \((a_n)\) defined by \[ a_n = 1 + \frac{1}{2} + \frac{1}{3} + \cdots + \frac{1}{n}. \] This sequence is increasing (by definition) and each \(a_n \leq 3\) by Exercise 7.9. By the Monotone Sequence Property, \((a_n)\) converges, which allows us to define one of the most famous numbers in all of mathematics, \[ \epsilon = 1 + \lim_{n \to \infty} a_n. \] ## Example 7.5 Fix \(0 < r < 1\). We claim that \(\lim_{n \to \infty} r^n = 0\). First, the sequence \((a_n = r^n)\) converges because it is decreasing and bounded below by 0. Let \(L = \lim_{n \to \infty} r^n\). By Proposition 7.3, \[ L = \lim_{n \to \infty} r^n = r^1 = \lim_{n \to \infty} r^n = 0. \] Thus \((1 - r)L = 0\) and (since \(1 - r \neq 0\)) we conclude that \(L = 0\). We remark that the Monotone Sequence Property implies the Least Upper Bound Property: every nonempty set of real numbers with an upper bound has a least upper bound. The Least Upper Bound Property, in turn, implies the following theorem, which is often stated as a separate axiom: **Footnote:** Both the Archimedean Property and the Least Upper Bound Property can be used in (different) axiomatic developments of \(\mathbb{R}\). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 131 Context: # Theorem 7.6. [Archimedean Property] If \( x \) is any real number then there is an integer \( N \) that is greater than \( x \). For a proof see Exercise 7.10. Theorem 7.6 essentially says that infinity is not part of the real numbers. Note that we already used Theorem 7.6 in Example 7.1. The Archimedean Property underlies the construction of an infinite decimal expansion for any real number, while the Monotone Sequence Property shows that such infinite decimal expansion actually converges to a real number. We close this discussion of limits with a pair of standard limits. The first of these can be established by calculus methods (such as L'Hôpital's rule (Theorem A.11), by treating \( x \) as the variable); both of them can be proved by more elementary considerations. Either way, we leave the proof of the following to Exercise 7.11. ## Proposition 7.7. (a) Exponential best polynomials: For any polynomial \( p(x) \) (with complex coefficients) and any \( x \in \mathbb{C} \) with \( |x| > 1 \), \[ \lim_{x \to \infty} \frac{p(x)}{e^x} = 0. \] (b) Factorials best exponentials: For any \( z \in \mathbb{C} \), \[ \lim_{n \to \infty} \frac{z^n}{n!} = 0. \] ## 7.2 Series **Definition.** A series is a sequence \( (a_n) \) whose members are of the form \( a_n = \sum_{k=1}^{n} b_k \) (or \( a_n = \sum_{k=1}^{\infty} b_k \)); we call \( (b_k) \) the sequence of terms of the series. The \( a_n = \sum_{k=1}^{n} b_k \) (or \( a = \sum_{k=1}^{\infty} b_k \)) are the partial sums of the series. If we wanted to be lazy we would define convergence of a series simply by referring to convergence of the partial sums of the series—after all, we just defined series through sums. However, there are some convergence features that hinge on special appearances for series, so we mention them here explicitly. For starters, a *Archimedes of Syracuse (287–212 BCE) attributes this property to Eudoxus of Cnidus (408–355 BCE). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 141 Context: for all \( n \in \mathbb{N} \). \[ \sum_{n=1}^N M_n - \sum_{n=1}^N M_n < \epsilon. \] Thus for all \( z \in G \) and \( n \in \mathbb{N} \): \[ \sum_{k=1}^{\infty} \left( f_k(z) - \sum_{k=1}^N f_k(z) \right) = \left| \sum_{k=1}^{\infty} f_k(z) \right| \leq \sum_{k=1}^N \left| f_k(z) \right| < \epsilon, \] which proves uniform convergence. Replace \( f_k \) with \( |f_k| \) in this argument to see that \( \sum_{k=1}^{\infty} |f_k| \) also converges uniformly. Example 7.29. We revisit Example 7.8 and consider the geometric series \( \sum_{k=1}^{\infty} z^k \) as a series of functions in \( z \). We know from Example 7.8 that this function series converges pointwise for \( |z| < 1 \): \[ \sum_{k=0}^{\infty} z^k = \frac{1}{1-z}. \] To study uniform convergence, we apply Proposition 7.28 with \( f(k) = z^k \). We need a series of upper bounds that converges, so fix a real number \( 0 < r < 1 \) and let \( M_k = M_r^k \). Then \[ |f_k(z)| = |z|^k < r^k \quad \text{for } |z| < r. \] And \( \sum_{k=1}^{\infty} r^k \) converges by Example 7.8. Thus, Proposition 7.28 says that \( \sum_{k=1}^{\infty} z^k \) converges uniformly for \( |z| < r \). We note the subtle distinction of domains for pointwise/uniform convergence: \[ \sum_{k=1}^{\infty} z^k \text{ converges (absolutely) for } |z| < 1, \text{ but to force uniform convergence, we need to shrink the domain to } |z| < r \text{ (arbitrary but fixed)} < 1. \] ### 7.4 Regions of Convergence For the remainder of this chapter (indeed, this book) we concentrate on some very special series of functions. **Definition.** A power series centered at \( z_0 \) is a series of the form \[ \sum_{k=0}^{\infty} c_k (z-z_0)^k \] where \( c_0, c_1, \ldots \in \mathbb{C} \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 143 Context: Now if \( |z - z_0| < r - |a| \), then \[ \sum_{k=0}^{\infty} |(z - z_0)^k|^p < \sum_{k=0}^{\infty} \frac{|(z - z_0)|^k}{r^k} \leq \frac{1}{1 - \frac{|z - z_0|}{r}}. \] The sum on the right-hand side is a convergent geometric sequence, since \( |z - z_0| < r \), and so \( \sum_{k=0}^{\infty} (z - z_0)^k \) converges absolutely by Corollary 7.12. **Proof of Theorem 7.31.** Consider the set \[ S = \left\{ x \in \mathbb{R}^2 : \sum_{k \neq 0} c_k (x - z_0)^k \text{ converges} \right\}. \] (This set is nonempty since \( 0 \in S \).) If \( R \) is unbounded, then \( \sum_{k \neq 0} c_k (z - z_0)^{-k} \) converges absolutely and uniformly for \( |z - z_0| < r \), for any \( r \) and so this gives the \( R = 0 \) case of Theorem 7.31: choose \( S \) with \( x \) such that \( R < R \). Then Proposition 7.32 says that \( \sum_{k} c_k (z - z_0)^k \) converges absolutely. Since \( |(z - z_0)|^k \leq |z - z_0|^k \), we can now use Proposition 7.28. If \( R \) is bounded, let \( R \) be its least upper bound. If \( R < \infty \), then \( \sum_{k \neq 0} c_k (z - z_0)^{-k} \) converges only for \( z \in R \), which establishes Theorem 7.31 in this case. Now assume \( R > 0 \). If \( |z - z_0| < R \) for some \( r < R \), again we can find \( z \) such that \( r < x < R \). Then \( \sum_{k} c_k |(z - z_0)|^k \) converges absolutely and uniformly for \( |z - z_0| < |z| \) by Proposition 7.13. This proves (b). Finally, if \( |z - z_0| > R \) then there exists \( r < R \) such that \[ |z - z_0| < R - |a|. \] But \( \sum_{k} c_k (z - z_0)^{-k} \) diverges, so by the contrapositive of Theorem 7.20, \( \sum_{k} |c_k| |(z - z_0)|^k \) diverges, and so by the contrapositive of Proposition 7.32, \( \sum_{k} c_k (z - z_0)^{-k} \) diverges, which finishes the proof. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 148 Context: # Power Series ![Functions](https://example.com/path/to/image) **Figure 7.3:** The functions \( f_n(x) = \sin\left(\frac{x}{n}\right) \) in Exercise 7.21. ## 7.18 1. Show that \[ \sum_{k=1}^{\infty} \frac{k}{k+1} \text{ diverges.} \] 2. Show that \[ \sum_{k=1}^{\infty} \frac{k}{k^2 + 1} \text{ converges.} \] ## 7.19 1. Suppose \( G \subset \mathbb{C} \) and \( f_n : G \to \mathbb{C} \) for \( n \geq 1 \). Suppose \( (a_n) \) is a sequence in \( \mathbb{R} \) with \( \lim_{n \to \infty} a_n = 0 \) and, for each \( n \geq 1 \), \[ |f_n(a_n)| \leq a_n \quad \text{for all } a \in G. \] Show that \( f_n \) converges uniformly to the zero function in \( G \). 2. Re-prove the statement of Example 7.24 using part (a). ## 7.20 1. Suppose \( G \subset \mathbb{C}, f_n : G \to \mathbb{C} \) for \( n \geq 1 \), and \( f_n \) converges uniformly to the zero function in \( G \). Show that if \( (a_n) \) is any sequence in \( G \), then \[ \lim_{n \to \infty} f_n(a_n) = 0. \] 2. Apply (a) to the function sequence given in Example 7.23, together with the sequence \( (b_n = \frac{1}{n}) \), to prove that the convergence given in Example 7.23 is not uniform. Image Analysis: ### Comprehensive Examination #### 1. Localization and Attribution - **Image Positioning and Numbering**: - **Image 1 (Top)**: Positioned at the upper part of the page. - **Image 2 (Middle)**: Text content starting from "7.18" to "7.20" located beneath the Image 1. #### 2. Object Detection and Classification - **Image 1**: - **Objects**: Graph/Chart depicting a series of curves. - **Classification**: Mathematical function graphs. #### 3. Scene and Activity Analysis - **Image 1**: - **Scene Description**: Graphical representation of functions \( f_n(x) = \sin^n(x) \) for different values of \( n \). - **Activity**: Visualization of function behavior as \( n \) increases, showing how the functions change shape. #### 4. Text Analysis - **Image 2**: - **Text Content**: - **Figure Caption**: "Figure 7.3: The functions \( f_n(x) = \sin^n(x) \) in Exercise 7.21." - **7.18**: Two parts (a) and (b) discussing convergence and divergence of series. - **7.19**: Two parts (a) and (b), with (a) detailing properties of a function sequence and convergence criteria; (b) asks to re-prove part (a). - **7.20**: Two parts (a) and (b), with (a) expanding on function convergence criteria and (b) applying these criteria to a given example. - **Significance**: The text provides mathematical exercises and explanations related to the visual content (graph of sin functions). #### 5. Diagram and Chart Analysis - **Image 1**: - **Diagram**: Graph of \( f_n(x) = \sin^n(x) \) - **Axes**: - **X-Axis**: Represents the variable \( x \). - **Y-Axis**: Represents the value of \( f_n(x) \). - **Scales**: Standard numerical scales for both x and y axes. - **Key Insights**: Demonstrates how the function \( f_n(x) \) narrows and approaches a delta-like function centered at \( \pi \) and other periodic points as \( n \) increases. #### 8. Color Analysis - **Image 1**: - **Dominant Colors**: Blue curves on a white background. - **Impact on Perception**: The color choice helps emphasize the variation among different curves, making it easy to distinguish between different values of \( n \). #### 9. Perspective and Composition - **Image 1**: - **Perspective**: Straight-on view of the graph. - **Composition**: Centralized graph with labeled axes. The curves are symmetric around the origin, following the properties of sine functions. #### 10. Contextual Significance - **Image 1**: - **Context**: Related to exercises and explanations in the study of power series and function convergence in mathematics. - **Contribution**: Provides visual understanding and concrete examples to complement the theoretical exercises below. #### 12. Graph Numbers - **Image 1**: - **Data Points**: Not explicitly provided, but the curves can be understood as sampled points from the functions \( \sin^n(x) \). - **Trends**: As \( n \) increases, the curve sharply peaks at specific points (multiples of \( \pi \)), demonstrating convergence behavior. #### 13. Graph and Trend Analysis - **Image 1**: - **Trends**: The sequence of functions \( f_n(x) = \sin^n(x) \) becomes more peaked at multiples of \( \pi \) as \( n \) increases, indicating how the function evolves with higher powers. - **Interpretation**: This trend is significant in understanding pointwise convergence and properties of Fourier series in mathematical analysis. #### Additional Aspects - **Prozessbeschreibungen (Process Descriptions)**: - **Series Convergence** (7.18): Analysis of divergence and convergence criteria. - **Function Sequence Convergence** (7.19, 7.20): Conditions and proof of uniform convergence of function sequences on given domains. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 149 Context: # REGIONS OF CONVERGENCE ## 7.21 Consider \( f_n : [0, \pi] \to \mathbb{R} \) given by \( f_n(x) = \sin(x/n) \) for \( n \geq 1 \). Prove that \( (f_n) \) converges pointwise to \( f : [0, \pi] \to \mathbb{R} \) given by \[ f(x) = \begin{cases} 1 & \text{if } x = 0 \\ 0 & \text{if } x \neq 0 \end{cases} \] yet this convergence is not uniform. (See Figure 7.3.) ## 7.22 Where do the following sequences converge pointwise? Do they converge uniformly on this domain? - (a) \( (a_n) \) - (b) \( \left(\frac{1}{n}\right) \) - (c) \( \left(\frac{1}{z}\right) \) where \( \text{Re}(z) \geq 0 \) ## 7.23 Let \( f(x) = x^k e^{-x} \). (a) Show that \( \lim_{n \to \infty} n f_n(x) = 0 \) for all \( x \geq 0 \). (Hint: Treat \( x = 0 \) as a special case; for \( x > 0 \), you can use L'Hôpital's rule (Theorem A.11) — but remember that \( x \) is the variable, not \( n \).) (b) Find \( \lim_{n \to \infty} \int_0^\infty f_n(x) \, dx \). (Hint: The answer is not \( 0 \).) (c) Why doesn't your answer to part (b) violate Proposition 7.27? ## 7.24 The product of two power series centered at \( x_0 \) is another power series centered at \( x_0 \). Derive a formula for its coefficients in terms of the coefficients of the original two power series. ## 7.25 Find a power series (and determine its radius of convergence) for the following functions. 1. \( \frac{1}{1 + 4x} \) 2. \( \frac{1}{3 - x} \) 3. \( \frac{x^2}{(4 - 2x)} \) ## 7.26 Find a power series representation about the origin of each of the following functions. - (a) \( \cos x \) - (b) \( \cos(z^2) \) - (c) \( z^2 \sin z \) - (d) \( \sin^2 x \) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 153 Context: # POWER SERIES AND HOLOMORPHIC FUNCTIONS A special case of this result concerns power series with infinite radius of convergence: those represent entire functions. Now that we know that power series are differentiable in their regions of convergence, we can also know how to find their derivatives. The next result says that we can similarly differentiate the series term by term. ## Theorem 8.2 Suppose \( f(z) = \sum_{k=0}^{\infty} c_k (z - z_0)^k \) has radius of convergence \( R > 0 \). Then \[ f'(z) = \sum_{k=1}^{\infty} k c_k (z - z_0)^{k-1} \quad \text{for any } z \in D_{[z_0,R]}. \] The radius of convergence of this power series is also \( R \). **Proof.** If \( z \in D_{[z_0,R]} \) then \( |z - z_0| < R \), so we can choose \( R' \) such that \( |z - z_0| < R' < R \). Then the circle \( \gamma = C(z_0,R') \) lies in \( D_{[z_0,R]} \) and is inside \( S \). Since \( f \) is holomorphic in \( D_{[z_0,R]} \), we can use Cauchy’s Integral Formula for \( f \) (Theorem 5.1), as well as Corollary 3.7: \[ f'(z) = \frac{1}{2 \pi i} \int_{\gamma} \frac{f(w)}{(w - z)^2} \, dw = \frac{1}{2 \pi i} \int_{\gamma} \frac{(w - z)^k}{(w - z)^2} \, dw = \sum_{k=0}^{\infty} k c_k \int_{\gamma} (w - z)^{k-1} \, dw \] Note that we used Theorem 5.1 again in the penultimate step, but now applied to the function \( f(w) \). The last statement of the theorem is easy to show: the radius of convergence of \( f'(z) \) is at least \( R \) since we have shown that the series for \( f' \) converges whenever \( |z - z_0| < R \), and it cannot be larger than \( R \) by comparison to the series for \( f(z) \), since the coefficients for \( (z - z_0)^{k-1} \) are larger than the corresponding ones for \( f(z) \). ## Example 8.3 Let \[ f(z) = \sum_{k=0}^{\infty} \frac{z^k}{k!}. \] #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 160 Context: # TAYLOR AND LAURENT SERIES Thus we can define a function \( g : G \rightarrow \mathbb{C} \) through \( g(z) = \begin{cases} \sum_{n=0}^{\infty} a_n (z - a)^n & \text{if } z \in D(a, R), \\ f(z) & \text{if } z \in G \setminus \{ a \}. \end{cases} \) (According to our calculations above, the two definitions give the same value when \( z \in D(a, R) \). The function \( g \) is holomorphic in \( D(a, R) \) by the first definition, and \( g \) is holomorphic in \( G \setminus \{ a \} \) by the second definition. Note that \( g(a) = c \neq 0 \) and, by construction, \( f(z) = (z - a)^n s(z) \quad \text{for all } z \in G. \) Since \( s(a) \neq 0 \) by continuity, \( r > 0 \) so that \( s(z) \neq 0 \) for all \( z \in D(a, r) \), so \( D(a, r) \) contains no other zero of \( f \). The integer \( r \) is unique, since it is defined in terms of the power series expansion of \( f \) at \( a \), which is unique by Corollary 8.6. Theorem 8.14 gives rise to the following result, which is sometimes called the identity principle or the uniqueness theorem. ## Theorem 8.15 Suppose \( G \) is a region, \( f : G \rightarrow \mathbb{C} \) is holomorphic, and \( f(a) = 0 \) where \( (a_k) \) is a sequence of distinct numbers that converges in \( G \). Then \( f \) is the zero function on \( G \). Applying this theorem to the difference of two functions immediately gives the following variant. ## Corollary 8.16 Suppose \( f \) and \( g \) are holomorphic in a region \( G \) and \( f(a) = g(a) = 0 \) at a sequence that converges to \( a \in G \) with \( a_k \neq a \) for all \( k \). Then \( f(z) = g(z) \) for all \( z \in G \). ### Proof of Theorem 8.15 Consider the following two subsets of \( G \): - \( X := \{ z \in G : \text{ there exists } z \text{ such that } F(z) = 0 \text{ for all } z \in D(a, r) \} \) - \( Y := \{ z \in G : \text{ there exists } z \text{ such that } F(z) \neq 0 \text{ for all } z \in D(a, r) \setminus \{ a \} \} \) If \( f(a) \neq 0 \) then, by continuity of \( f \), there exists a disk centered at \( a \) in which \( f \) is nonzero, and so \( a \in Y \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 161 Context: # CLASSIFICATION OF ZEROS AND THE IDENTITY PRINCIPLE If \( f(z) = 0 \), then Theorem 8.14 says that either \( z \in X \) or \( z \) is an isolated zero of \( f \), so \( z \in V \). We have thus proved that \( G \) is the disjoint union of \( X \) and \( Y \). Exercise 8.11 proves that \( X \) and \( Y \) are open, and so (because \( G \) is a region) either \( X \) has to be empty. The conditions of Theorem 8.15 say that \( z_1, z_2, \ldots \) is not in \( V \), and this has to be in \( X \). Thus \( G = X \) and the statement of Theorem 8.15 follows. The identity principle yields the strengthenings of Theorem 6.11 and Corollary 6.12 promised in Chapter 6. We recall that we say the function \( f: G \to \mathbb{C} \) has a weak relative maximum if there exists a disk \( D(z_r, r) \subset G \) such that all \( z \in D(z_r, r) \) satisfy \( |f(z)| \leq |f(z_r)| \). ## Theorem 8.17 (Maximum-Modulus Theorem). Suppose \( f \) is holomorphic and nonconstant in a region \( G \). Then \( |f| \) does not attain a weak relative maximum in \( G \). There are many reformulations of this theorem, such as: ### Corollary 8.18. Suppose \( f \) is holomorphic in a bounded region \( G \) and continuous on its closure. Then \[ \sup_{z \in \partial G} |f(z)| = \max_{z \in \overline{G}} |f(z)|. \] **Proof.** This is trivial if \( f \) is constant, so we assume \( f \) is non-constant. By the Extreme Value Theorem, if there is a point \( z_r \in G \) such that \( \max_{z \in \overline{G}} |f(z)| \). Clearly \( \sup_{z \in |f(z)|} \geq \max_{z \in |f(z)|} \); and this is easily seen to be an equality using continuity at \( z_r \) since there are points of \( G \) arbitrarily close to \( z_r \). Finally, Theorem 8.17 implies \( f \) is not constant in \( G \). ### Corollary 8.19 (Minimum-Modulus Theorem). Suppose \( f \) is holomorphic and nonconstant in a region \( G \). Then \( |f| \) does not attain a weak relative minimum at a point \( z \in G \) unless \( f(z) = 0 \). ### Corollary 8.20. If \( f \) is harmonic and nonconstant in a region \( G \), then it does not have a weak relative maximum or minimum in \( G \). Note that Equation (6.1) in Chapter 6 follows from Corollary 8.20 using essentially the same argument as in the proof of Corollary 8.18. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 163 Context: Here \( a_k \in \mathbb{C} \) are terms indexed by the integers. The double series above converges if and only if the two series on the right-hand side do. Absolute and uniform convergence are defined analogously. Equipped with this, we can now introduce the following central concept. ## Definition A Laurent series centered at \( z_0 \) is a double series of the form \[ \sum_{n \in \mathbb{Z}} c_n (z - z_0)^{n}. \] ### Example 8.21 The series that started this section is the Laurent series of \(\exp\left(\frac{1}{z}\right)\) centered at 0. ### Example 8.22 Any power series is a Laurent series (with \( a_k = 0 \) for \( k < 0 \)). We should pause for a minute and ask for which \( z \) a general Laurent series can possibly converge. By definition, \[ \sum_{n \in \mathbb{Z}} c_n (z - z_0)^n = \sum_{n \geq 0} c_n (z - z_0)^n + \sum_{n < 0} c_n (z - z_0)^n. \] The first series on the right-hand side is a power series with some radius of convergence \( R_z \), that is, with Theorem 7.31, it converges in \( \{ z \in \mathbb{C} : |z - z_0| < R_z \} \), and the convergence is uniform in \( \{ z \in \mathbb{C} : |z - z_0| \leq r \} \) for any fixed \( r < R_z \). For the second series, we invite you (in Exercise 8.30) to revise our proof of Theorem 7.31 to show that this series converges for \[ \frac{1}{|z - z_0|} < \frac{1}{R_1} \] for some \( R_1 \), and that the convergence is uniform in \( \{ z \in \mathbb{C} : |z - z_0| \leq r \} \) for any \( r > R_1 \). Thus the Laurent series converges in the annulus \[ A = \{ z \in \mathbb{C} : R_1 < |z - z_0| < R_2 \} \] (assuming this set is not empty, i.e., \( R_1 < R_2 \)), and the convergence is uniform on any set of the form \[ \{ z \in \mathbb{C} : R_1 < |z - z_0| < r \} \] for \( R_1 < r < R_2 \). *Jean-Pierre Antoine Laurent (1813–1894).* #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 172 Context: 8.24. Prove: If \( f \) is entire and \( \text{Im}(f) \) is constant on the closed unit disk then \( f \) is constant. 8.25. (a) Find the Laurent series for \( \frac{1}{z^2} \) centered at \( z = 0 \). (b) Prove that \( f: \mathbb{C} \to \mathbb{C} \) is entire, where \[ f(z) = \begin{cases} \frac{1}{z} & \text{if } z \neq 0 \\ -1 & \text{if } z = 0 \end{cases} \] 8.26. Find the Laurent series for \( \sec(z) \) centered at the origin. 8.27. Suppose that \( f \) is holomorphic at \( z_0 \), \( f(z_0) = 0 \), and \( f'(z_0) \neq 0 \). Show that \( f \) has a zero of multiplicity 1 at \( z_0 \). 8.28. Find the multiplicities of the zeros of each of the following functions: (a) \( f(z) = e^{z} - 1 \), \( z_0 = 2k\pi i \), where \( k \) is any integer. (b) \( f(z) = \sin(z) - \tan(z) \), \( z_0 = 0 \). (c) \( f(z) = \cos(z) - 1 + z^2 \sin'(z_0) \), \( z_0 = 0 \). 8.29. Find the zeros of the following functions and determine their multiplicities: (a) \( 1 + z^2 \) (b) \( \sin(z) \) (c) \( z^2 \cos(z) \) 8.30. Prove that the series of the negative-index terms of a Laurent series \[ \sum_{k < 0} c_k (z - z_0)^k \] converges for \[ \frac{1}{R_1} < |z - z_0| < \frac{1}{R_0} \] for some \( R_1 \), and that the convergence is uniform in \( \{ z \in \mathbb{C} : |z - z_0| \geq r_1 \} \) for any fixed \( r_1 < R_1 \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 174 Context: # TAYLOR AND LAURENT SERIES ### 8.36. (a) Find a Laurent series for \[ \frac{1}{(z^2 - 4)(z - 2)} \] centered at \( z = 2 \) and specify the region in which it converges. (b) Compute \[ \int_{C_{[1]}} \frac{dz}{(z^2 - 4)(z - 2)}. \] ### 8.37. (a) Find the power series of \( \exp(z) \) centered at \( z = -1 \). (b) Compute \[ \int_{C_{[-2]}} \frac{\exp(z)}{(z + 1)^3} dz. \] ### 8.38. Compute \[ \int \frac{\exp(z)}{\sin(z)} dz \] where \( \gamma \) is a closed curve not passing through integer multiples of \( \pi \). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 175 Context: # Chapter 9 ## Isolated Singularities and the Residue Theorem \(\frac{1}{z}\) has a nasty singularity at \(z = 0\), but it did not bother Newton—the reason is far enough. Edward Witten We return one last time to the starting point of Chapters 7 and 8: the quest for \[ \int_{C} \frac{\exp(z)}{\sin(z)} \, dz. \] We computed this integral in Example 8.28 crawling on hands and knees (but we finally computed it), by considering various Taylor and Laurent expansions of \(\exp(z)\) and \(\frac{1}{\sin(z)}\). In this chapter, we develop a calculus for similar integral computations. ## 9.1 Classification of Singularities What are the differences among the functions \(\frac{\exp(z)}{z}\), \(\frac{1}{z}\), and \(\exp(z)\) at \(z = 0\)? None of them are defined at \(0\), but each singularity is of a different nature. We will frequently consider functions in this chapter that are holomorphic in a disk except at its center (usually because that’s where a singularity lies), and it will be handy to define the punctured disk with center \(z_0\) and radius \(R\), \[ D(z_0, R) = \{ z \in \mathbb{C} : 0 < |z - z_0| < R \}. \] We extend this definition naturally with \(D[z_0, R] = \{ z \in \mathbb{C} : |z - z_0| \leq R \}\). For complex functions there are three types of singularities, which are classified as follows: #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 179 Context: # CLASSIFICATION OF SINGULARITIES on \( D[\alpha, R] \) and non-zero at \( \alpha_n > 0 \), and \( f(z) = \frac{g(z)}{z - \alpha} \) for all \( z \in D[\alpha, R] \). But then \( \alpha \) is a pole of order \( m \) since \[ \lim_{z \to \alpha} |f(z)| = \lim_{z \to \alpha} \left| \frac{g(z)}{(z - \alpha)^m} \right| = \lim_{z \to \alpha} \frac{|g(z)|}{|z - \alpha|^m} = \infty. \] We underline one feature of the last part of our proof: ## Corollary 9.6 Suppose \( f \) is holomorphic in \( D[\alpha, R] \). Then \( f \) has a pole at \( \alpha \) if and only if there exists a positive integer \( m \) and a holomorphic function \( g : D[\alpha, R] \to \mathbb{C} \) such that \( g(\alpha) \neq 0 \) and \[ f(z) = \frac{g(z)}{(z - \alpha)^m} \] for all \( z \in D[\alpha, R] \). If \( \alpha \) is a pole then \( m \) is unique. ### Proof The only part not covered in the proof of Theorem 9.5 is uniqueness of \( m \). Suppose \( f(z) = \frac{(z - \alpha)^{m}}{g(z)} \) and \( f(z) = \frac{(z - \alpha)^{n}}{h(z)} \) both work, with \( m > n \). Then \( g(z) = (z - \alpha)^{m - n} h(z) \), and plugging in \( z = \alpha \) yields \( g(\alpha) = 0 \), violating \( g(\alpha) \neq 0 \). ### Definition The integer \( m \) in Corollary 9.6 is the order of the pole \( \alpha \). This definition, naturally coming out of Corollary 9.6, parallels that of the multiplicity of a zero, which naturally came out of Theorem 8.14. The two results also show that if \( f \) has a zero at \( \alpha \) of multiplicity \( m \) and only if \( j \) has a pole of order \( m \), we will make use of the notions of zeros and poles quite extensively in this chapter. You might have noticed that the Proposition 9.5 did not include any results on essential singularities. Not only does the next theorem make up for this but it also nicely illustrates the strangeness of essential singularities. To appreciate the following result, we suggest meditating about its statement over a good cup of coffee. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 180 Context: ```markdown # Theorem 9.7 (Casorati–Weierstrass) If \( f \) is an essential singularity of \( r \) and \( r \) is any positive real number, then every \( u \in C \) is arbitrarily close to a point in \( f(B(z_0, r)) \). That is, for any \( x \in C \) and \( \epsilon > 0 \) there exists \( z \in B(z_0, r) \) such that \( |u - f(z)| < \epsilon \). In the language of topology, Theorem 9.7 says that the image of any punctured disk centered at an essential singularity is dense in \( C \). There is a stronger theorem, beyond the scope of this book, which implies the Casorati–Weierstrass Theorem 9.7. It is due to Charles Émile Picard (1856–1941) and says that the image of any punctured disk centered at an essential singularity misses at most one point of \( C \). (It is worth coming up with examples of functions that do not miss any point in \( C \) and functions that miss exactly one point. Try it!) ## Proof Suppose (by way of contradiction) that there exists \( w \in C \) and \( \epsilon > 0 \) such that for all \( z \in B(z_0, r) \) \[ |u - f(z)| \geq \epsilon. \] Then the function \( g(z) = \frac{f(z) - w}{z - z_0} \) stays bounded as \( z \to z_0 \) and so \[ \lim_{z \to z_0} (z - z_0) g(z) = \lim_{z \to z_0} \frac{f(z) - w}{z - z_0} = 0. \] (Proposition 9.5(a) tells us that \( f \) has a removable singularity at \( z_0 \).) Hence \[ \lim_{z \to z_0} \left| \frac{f(z) - w}{z - z_0} \right| = \infty \] and so the function \( f(z) - w \) has a pole at \( z_0 \). By Proposition 9.5(b), there is a positive integer \( n \) so that \[ \lim_{z \to z_0} (z - z_0)^{n+1} f(z) = \lim_{z \to z_0} (z - z_0)^n g(f(z)) = 0. \] Invoking Proposition 9.5 again, we conclude that the function \( f(z) \) has a pole or removable singularity at \( z_0 \), which implies the same holds for \( f(z) \), a contradiction. ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 185 Context: ```markdown # RESIDUES **Proof:** The functions \( f \) and \( g \) have power series centered at \( z_0 \); the one for \( g \) has by assumption no constant term: \[ f(z) = \sum_{n=0}^{\infty} a_n (z - z_0)^n \] \[ g(z) = \sum_{n=1}^{\infty} b_n (z - z_0)^n \] Let \( h(z) = \sum_{n=1}^{\infty} b_n (z - z_0)^{-n} \) and note that \( h(z_0) = b_1 \neq 0 \). Hence, \[ \frac{f(z)}{g(z)} = \frac{f(z)}{(z - z_0) h(z)} \] and the function \( \frac{f(z)}{g(z)} \) is holomorphic at \( z_0 \). By Prop 9.11 and Taylor's formula (Corollary 8.5), \[ \text{Res}_{z \to z_0} \left( \frac{f(z)}{g(z)} \right) = \lim_{z \to z_0} \left( (z - z_0) \frac{f(z)}{g(z)} \right) = \frac{f(z_0)}{h(z_0)} \frac{f(z)}{h(z)} \cdot \frac{d}{dz} \frac{f(z)}{g(z)} \Big|_{z=z_0} \] Example 9.15. Revisiting once more Example 8.28, we note that \( f(z) = e^{z} \) and \( g(z) = \sin(z) \) fill the bill. Thus, \[ \text{Res}_{z \to 0} \left( \frac{e^{z}}{\sin(z)} \right) = \frac{e^0}{\cos(0)} = 1 \] and confirming once more our computations in Examples 8.28 and 9.12. Example 9.16. We compute the residue of \( \frac{e^{z} + z^2}{e^{2z} - z^2} \) at \( z_0 = 2\pi i \), by applying Proposition 9.14 with \( f(z) = e^{z} + z^2 \) and \( g(z) = e^{2z} - z^2 \). Thus, \[ \text{Res}_{z \to 2\pi i} \left( \frac{e^{z} + z^2}{e^{2z} - z^2} \right) = \frac{-4\pi^2 + 2}{\cosh(2\pi)} \] An extension of Proposition 9.14 of sorts is given in Exercise 9.12. ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 189 Context: # ARGUMENT PRINCIPLE AND ROUCHÉ'S THEOREM This theorem is of surprising practicality. It allows us to locate the zeros of a function fairly precisely. Here is an illustration. ## Example 2.19 All the roots of the polynomial \( p(z) = z^5 + z^4 + z^3 + z^2 + z + 1 \) have modulus less than two. To see this, let \( f(z) = z^5 + z^4 + z^3 + z^2 + z + 1 \). For \( z \in [0, 2] \): \[ |f(z)| \leq |z^5| + |z^4| + |z^3| + |z^2| + |z| + 1 = 16 + 8 + 4 + 2 + 1 = 31 < 32 = |z^5| \text{ for } z \in [\sqrt{2}, 2]. \] So \( g \) and \( f \) satisfy the condition of Theorem 9.18. But \( f \) has just one root, of multiplicity 5 at the origin, whence \[ Z(f) \cap (C[0, 2]) = Z(f + g, C[0, 2]) = Z(f, C[0, 2]) = 5. \] ### Proof of Theorem 9.18 By (9.1) and the Argument Principle (Theorem 9.17): \[ Z(f + g, r) = \frac{1}{2\pi i} \int_{\gamma} \frac{f + g}{f + g} \, \frac{(f + g)'}{f + g} \, dz = \frac{1}{2\pi i} \int_{\gamma} \frac{(f + g)'}{f + g} \, dz, \] where \( \gamma \) is a contour around \( r \). We are assuming that \( |g| < |f| \) on \( \gamma \), which means that the function \( \frac{1}{f + g} \) evaluated on \( \gamma \) stays away from \( R_+ \). But then \( \log\left(\frac{1}{f + g}\right) \) is a well-defined holomorphic function on \( \gamma \). Its derivative is \[ \frac{(f + g)'}{f + g}. \] --- > *The Fundamental Theorem of Algebra (Theorem 5.1) asserts that \( p \) has \( n \) roots in \( C \). What's special about the theorem of Example 2.19 is that they all have modulus < 2. Note also that there is no general formula for composing roots of a polynomial of degree \( n \). Although for this \( n \) it’s not hard to find one root—and therefore all of them.* #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 193 Context: # Argument Principle and Rouche's Theorem ## 9.21. Find the number of zeros of 1. \( 3z^2 - z \) in \( D[0, 1] \) 2. \( \{ z \} \in D[0, 1] \) 3. \( e^{-z} - 5 + 1 \) in \( \{ z \in \mathbb{C} : |z| \leq 2 \} \) ## 9.22. Give another proof of the Fundamental Theorem of Algebra (Theorem 5.11), using Rouche's Theorem 9.18. *(Hint: If \( p(z) = z^n + a_{n-1}z^{n-1} + \ldots + a_0 \), let \( f(z) = a_n z^n \) and \( g(z) = a_{n-1}z^{n-1} + a_{n-2}z^{n-2} + \ldots + a_0 \), and choose \( r \) a circle that is large enough to make the condition of Rouche's theorem work. You might want to first apply Proposition 5.10 to \( g(z) \).)* ## 9.23. Suppose \( S \subset C \) is closed and bounded and all points of \( S \) are isolated points of \( S \). Show that \( S \) is finite, as follows: (a) For each \( x \in S \), we can choose \( \varepsilon > 0 \) so that \( D[x, \varepsilon] \) contains no points of \( S \) except \( x \). Show that \( f \) is continuous. *(Hint: This is really easy if you use the first definition of continuity in Section 2.1.)* (b) Assume \( S \) is non-empty. By the Extreme Value Theorem A.1, \( S \) has a minimum value, \( r_0 > 0 \). Let \( r = r_0/2 \). Since \( S \) is bounded, it lies in a disk \( D[0, M] \) for some \( M > 0 \). Show that the small disks \( D[x, r] \) for \( x \in S \) are disjoint and lie in \( D[0, M+r] \). (c) Find a bound on the number of such small disks. *(Hint: Compare the areas of \( D[x, r] \) and \( D[0, M + r] \).)* #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 195 Context: # Binomial Coefficients (4) Evaluate \(\sum_{n=1}^{\infty} \frac{1}{n^2}\). (5) Repeat the exercise with the function \(f(z) = \frac{z^{-1}}{e^{z} - 1}\) to arrive at an evaluation of \[ \sum_{n=1}^{\infty} \frac{(-1)^{n}}{n^2}. \] (Hint: To bound this function, you may use the fact that \(\frac{1}{e^z - 1} = 1 + \cos(z_n)\).) (6) Evaluate \(\sum_{n=1}^{\infty} n\) and \(\sum_{n=1}^{\infty} n^{-1}\). We remark that, in the language of Example 7.21, you have computed the evaluations \(\zeta(2)\) and \(\zeta(4)\) of the Riemann zeta function. The function \(\zeta'(s) := \sum_{n=1}^{\infty} \frac{1}{n^s}\) is called the alternating zeta function. ## 10.2 Binomial Coefficients The binomial coefficient \(\binom{n}{k}\) is a natural candidate for being explored analytically, as the binomial theorem states: \[ (x + y)^n = \sum_{k=0}^{n} \binom{n}{k} x^{k} y^{n-k} \] (for \(x, y \in \mathbb{C}\) and \(n \in \mathbb{Z}_{\geq 0}\)) tells us that \(\binom{n}{k}\) is the coefficient of \(x^{k}\) in \((x + y)^{n}\). You will derive two simple identities in the course of the exercises below. 1. Convince yourself that \[ \binom{n}{k} = \frac{1}{2\pi i} \oint_{C} \frac{(x + 1)^{n}}{z^{k + 1}} dz, \] where \(C\) is any simple closed piecewise smooth path such that \(0\) is inside \(r\). 2. Derive a recurrence relation for binomial coefficients from the fact that \[ \frac{1}{z^{n}} = \frac{1}{2^{n}} \cdot \left( \text{Multiply both sides by } \frac{1}{z^{n}}\right). \] 3. Now suppose \(z\) is such that \(|z| < 1/4\). Find a simple path \(P\) surrounding the origin such that \[ \sum_{n=0}^{\infty} \left( \frac{(z + 1)^{k}}{k} \right) \] converges uniformly on \(y\) as a function of \(\epsilon\). Evaluate this sum. #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 196 Context: ``` Keeping \( x \) and \( y \) from (3), convince yourself that \[ \sum_{k=0}^{\infty} \left( \frac{2k}{k} \right) k^k = \frac{1}{2\pi i} \int \left( \frac{x^{n+1}}{z^{n+1}} \right) dz, \] use (3) to interchange summation and integral, and use the Residue Theorem 9.10 to evaluate the integral, giving an identity for \( \sum_{k=0}^{\infty} \left( \frac{1}{2} \right)^k \). ### 10.3 Fibonacci Numbers The Fibonacci\(^1\) numbers are a sequence of integers defined recursively through \[ f_0 = 0, \] \[ f_1 = 1, \] \[ f_n = f_{n-1} + f_{n-2} \quad \text{for } n \geq 2. \] Let \( F(z) = \sum_{n=0}^{\infty} f_n z^n \). 1. Show that \( F \) has a positive radius of convergence. 2. Show that the recurrence relation among the \( f_n \) implies that \( F(z) = \frac{z}{1 - z - z^2} \). (Hint: Write down the power series for \( F(z) \) and \( z^2 F(z) \) and rearrange both so that you can easily add.) 3. Verify that \[ \text{Res}_{z=0} \left( \frac{1}{z(1 - z - z^2)} \right) = f_0. \] 4. Use the Residue Theorem 9.10 to derive an identity for \( f_n \). (Hint: Integrate \[ \frac{1}{z(1 - z - z^2)} \] around \( C[0, R] \) and show that this integral vanishes as \( R \to \infty \). \(^1\) Named after Leonardo Pisano Fibonacci (1170–1250). ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 197 Context: # The Coin-Exchange Problem (5) Generalize to other sequences defined by recurrence relations, e.g., the Fibonacci numbers - \( t_0 = 0 \) - \( t_1 = 0 \) - \( t_2 = 1 \) - \( t_n = t_{n-1} + t_{n-2} + t_{n-3} \) for \( n \geq 3 \). ## 10.4 The Coin-Exchange Problem In this exercise, we will solve and extend a classical problem of Ferdinand Georg Frobenius (1849–1917). Suppose \( a \) and \( b \) are relatively prime positive integers, and suppose \( r \) is a positive integer. Consider the function \[ f(c) = \frac{1}{(1 - z)(1 - z^2)z^r} \] 1. Compute the residues at all nonzero poles of \( f \). 2. Verify that \( Res_{z = 0}(f) = N(r) \), where \[ N(r) = \{(m, n) \in \mathbb{Z}^2 : m \geq 0, n \geq 0, m + nb = r\} \]. 3. Use the Residue Theorem, Theorem 9.10, to derive an identity for \( N(r) \). (Hint: Integrate \( f \) around \( [0, R] \) and show that this integral vanishes as \( R \to \infty \).) 4. Use the following three steps to simplify this identity to \[ N(t) = \frac{1}{ab} \left( \frac{b-1}{a} - \left( \frac{a-1}{b} \right) \right) + 1. \] *This means that the integers do not have any common factor.* #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 198 Context: # Discrete Applications of the Residue Theorem Here, \(\{x_n\}\) denotes the fractional part of \(x\): \(a_n \equiv 1 \,(\text{mod } b)\), and \(b \cdot 6 \equiv 1 \,(\text{mod } d)\). ## (a) Verify that for \(b = 1\), \[ N(n) = \left| \{(m,n) \in \mathbb{Z}^2 : m \geq 0, n + n \leq s \} \right| = \left| \{ m \in \mathbb{Z} : m \geq 0, m \cdot s \leq 1 \} \right| = \left[ \frac{0}{d} \right] n^2 = \left\lfloor \frac{1}{d} \right\rfloor. \] ## (b) Use this together with the identity found in (3) to obtain: \[ -\frac{1}{2} \sum_{k=1}^{\infty} \frac{1}{(1 - 2e^{2\pi i k})\cdot 2k} = \left( -\frac{1}{2} + \frac{1}{2} \right) + \frac{1}{z} \, \] ## (c) Verify that \[ \sum_{k=1}^{\infty} \frac{1}{(1 - 2e^{2\pi i k})} = \sum_{k=1}^{\infty} \frac{1}{(1 - 2e^{2\pi i k})} \] ## (5) Prove that \(N(a - b) = 0\), and \(N(n) > 0\) for all \(x > a\) and \(x < b\). ### Historical Remark Given relatively prime positive integers \(a_1, a_2, \ldots\), let’s call an integer \(t\) representable if there exist nonnegative integers \(m_1, m_2, \ldots, m_k\) such that \[ t = m_1 a_1 + m_2 a_2 + \cdots + m_k a_k. \] (There are many scenarios in which you may ask whether or not \(t\) is representable, given fixed \(a_1, a_2, \ldots, a_k\); for example, if the \(a_i\) are co-prime, this question asks whether you can give exact change for \(t\). In the late 19th century, Frobenius raised the problem of finding the largest integer that is not representable. We will call this largest integer the Frobenius number \(g(a_1, a_2, \ldots, a_k)\). It is well known (probably at least since the 1880s, when James Joseph Sylvester (1814–1897) studied the Frobenius problem) that \(g(a_1, a_2) = a_1 a_2 - a_1 - a_2\). You verified this result in (5). For \(x > 2\), there is no closed formula for \(g(a_1, a_2, \ldots, a_k)\). The formula in (4) states that The fractional part of a real number \(x\) is loosely speaking the part after the decimal point. More thoroughly, the principal integer function of \(x\), denoted by \(\lfloor x \rfloor\), is the largest integer not exceeding \(x\). The fractional part is defined as \( \{x\} = x - \lfloor x \rfloor \). **"This means that \(c\) is an integer such that \(c = a + 1 + b + k\) for some \(k \in \mathbb{Z}\)."** #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 200 Context: # Discrete Applications of the Residue Theorem ## Historical Remark The sum in (10.1) is called a Dedekind* sum. It first appeared in the study of the Dedekind \( \eta \)-function \[ \eta(z) = \exp\left(\frac{\pi i}{12} z\right) \prod_{n=1}^{\infty} \left(1 - \exp(2 \pi i n z)\right) \] in the 1870s and has since intrigued mathematicians from such different areas as topology, number theory, and discrete geometry. The reciprocity law (10.2) is the most important and famous identity of the Dedekind sum. The proof that is outlined here is due to Hans Rademacher (1892–1969). --- *Named after Julius Wilhelm Richard Dedekind (1831–1916). #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 204 Context: # Solutions to Selected Exercises Well here's another clue for you all. John Lennon & Paul McCartney ("Glass Onion," *The White Album*) ## 1.1 (a) \( 7 - i \) (b) \( 1 - i \) (c) \( -11 - 2i \) (d) \( -2 + 3i \) ## 1.2 (b) \( \frac{1}{3} - \frac{1}{2} i \) ## 1.3 (a) \( \sqrt{5}, -2 \) (b) \( 5\sqrt{5}, 5 - 10i \) (c) \( \frac{\sqrt{2 - 1} + \sqrt{(2 + \sqrt{9})}}{5} \) (d) \( 8 \) ## 1.4 (a) \( 2^{1/2} i \) (b) \( 2\sqrt{5}i^2 e^{2} \) (c) \( e^{5} \) ## 1.5 (a) \( -1 + i \) (b) \( 34i \) (c) \( -1 \) (d) \( 2 \) ## 1.9 \( e^{i \pi} = -1 \) ## 1.11 (a) \( x = e^{i k}, k = 0, 1, \ldots, 5 \) (b) \( x = 2 e^{i t^{5/4}}, k = 0, 1, 2, 3 \) ## 1.18 \( \cos \frac{\pi}{5} \) and \( \sin \frac{3\pi}{5} \) ## 1.33 For instance: (a) \( r(t) = (1 + i)t + e^{it}, 0 \leq t < 2\pi \). (b) \( r(t) = (2 - i)(1 - i)(2i) + (2)(1 + i + 3i), 0 \leq t \leq 1 \). (c) \( r(t) = 34e^{-i \pi} = 34e^{-i(t)}, 0 \leq t \leq \pi \). ## 2.2 (a) \( 1 + i \) ## 2.18 (a) differentiable and holomorphic in \( C \) with derivative \( e^{-z} e^{z} \) (b) nowhere differentiable or holomorphic (c) differentiable only on \( x + iy \in C : x = y \) with derivative \( 2x \), nowhere #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 205 Context: # Holomorphic Functions (a) nowhere differentiable or holomorphic (b) differentiable and holomorphic in \( \mathbb{C} \) with derivative \(-\sin(x) + i\cos(y)\) (c) nowhere differentiable or holomorphic (d) differentiable only at \(0\) with derivative \(2y - 2xi = -2iz\) (e) differentiable only at \(0\) with derivative \(0\), nowhere holomorphic (f) differentiable only at \(y\) with derivative \(0\), nowhere holomorphic (g) differentiable only at \(0\) with derivative \(0\), nowhere holomorphic (h) differentiable only at \(0\) with derivative \(h\), nowhere holomorphic (i) differentiable only at \(y\) with derivative \(0\), nowhere holomorphic (j) differentiable and holomorphic in \( \mathbb{C} \) with derivative \(2y - 2xi = -2iz\) (k) differentiable only at \(0\) with derivative \(0\), nowhere holomorphic (l) differentiable only at \(0\) with derivative \(0\), nowhere holomorphic ## 2.25 (a) \(2xy\) (b) \(\cos(x)\sinh(y)\) ## 2.26 Neither is defined at the origin, nor continuously extendable to the origin, so neither is harmonic on all of \( \mathbb{C} \). Away from the origin, the first is harmonic, while the second is not. ## 3.14 (a) \(\frac{2x+1}{x-3}\) (b) \(\frac{(i-1)z+1}{iz-2}\) (c) \(\frac{z-1}{z+i}\) ## 3.40 (a) \(\ln(2) + \frac{1}{z}\) (b) \(e^z \cdot \left( c \ln(2) + \frac{1}{z^2} \right)\) ## 3.44 (a) differentiable at \(0\), nowhere holomorphic (b) differentiable and holomorphic on \(C \backslash \{-1, -e^{-1}, e^{-i}\}\) (c) differentiable and holomorphic on \(C \backslash \{x + iy \in \mathbb{C} : x \leq -1, y = 2\}\) (d) nowhere differentiable or holomorphic (e) differentiable and holomorphic on \(C \{x + iy \in \mathbb{C} : x \leq 3, y = 0\}\) (f) differentiable and holomorphic in \( \mathbb{C} \) (i.e. entire) ## 3.45 (a) \(z = e^{z}\) (there is no solution) (b) \(z = \ln z + k\pi i\) for \(k \in \mathbb{Z}\) (c) \(z = \frac{1}{2}z + k i\), where \(k \in \mathbb{Z}\) (d) \(z = \frac{j}{2} + k i\), where \(j \in \mathbb{Z}\) (e) \(z = nk\), where \(n, k \in \mathbb{Z}\) (i.e. \(z = 2i\)) ## 3.50 \(f'(z) = e^{z}\) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 206 Context: 200 # Solutions to Selected Exercises ## 4.1 (a) \(6\) (b) \(\pi\) (c) \(4\) (d) \(\sqrt{7} + \frac{1}{2} \sinh^{-1}(4)\) ## 4.5 (a) \(8i\) (b) \(0\) (c) \(0\) ## 4.6 (a) \(1-i\) (b) \(i\pi, -\pi, 0, 2\pi\) (c) \(i^2, -2, 0, 2r^2\) ## 4.7 (a) \(\frac{1}{3} (e^{3z} - e^{-3z})\) (b) \(0\) (c) \(\{g(\exp(3 + 3i)) - 1\}\) ## 4.12 \(\sqrt{3} i\) ## 4.18 (a) \(-4 + i\left(4 + \frac{1}{3}\right)\) (b) \((\ln(17) - 1) + i \left(\frac{\pi}{4} + 1\right)\) (c) \(2\sqrt{2} - 1 + 2i\sqrt{2}\) (d) \(\frac{1}{4} \sin(8) - 2 + i \left(2 - \frac{1}{4} \sinh(8)\right)\) ## 4.27 For \(|r| < |z| \Rightarrow 2\pi for \ |r| < |z|\) ## 4.30 \(\frac{24}{30}\) ## 4.34 \(0\) ## 4.35 For \(r = 1\): \( \frac{-1}{3} \); for \(r = 3\): \(0\); for \(r = 5\) ## 4.37 (a) \(2\pi\) (b) \(0\) (c) \(-\frac{3}{2}\) (d) \(\frac{2}{2r^2 - 1}\) ## 5.1 (a) \(2\pi\) (b) \(-6i\) (c) \(\pi\) (d) \(0\) ## 5.3 (a) \(0\) (b) \(2\pi i\) (c) \(0\) (d) \(\pi\) (e) \(f(0)\) ## 5.4 \(2\pi \exp{(iw)}\) ## 5.18 \(\frac{\sqrt{3}}{2}\) ## 5.20 \(\frac{\sqrt{z}}{\sin{\left(\frac{1}{\sqrt{2}} z\right)}}\) ## 7.1 (a) Divergent (b) Convergent (limit \(0\)) (c) Divergent (d) Convergent (limit \(2 -\frac{1}{2}\)) (e) Convergent (limit \(0\)) ## 7.3 \(\sum_{n=2}^{\infty} (-4)^n z^n = \sum_{n=3}^{\infty} \frac{1}{6} z^n = \frac{k + 1}{2} z^{n+2}\) #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 208 Context: # Index - **absolute convergence**, 129 - **absolute value**, 5 - **accumulation point**, 13, 24 - **addition**, 2 - **algebraically closed**, 103 - **alternating harmonic series**, 131 - **alternating zeta function**, 189 - **analytic**, 152 - **analytic continuation**, 158 - **antiderivative**, 76, 100, 196 - **Arg**, 59 - **arg**, 60 - **argument**, 5 - **axis** - imaginary, 5 - real, 5 - **bijection**, 31, 43 - **binary operation**, 2 - **binomial coefficient**, 189 - **boundary**, 13, 117 - **boundary point**, 13 - **bounded**, 13 - **branch of the logarithm**, 59 - **calculus**, 1, 195 - **Casorati–Weierstrass theorem**, 173 - **Cauchy's estimate**, 151 - **Cauchy's integral formula**, 85 - **extensions of**, 97, 151 - **Cauchy's theorem**, 81 - **Cauchy–Goursat theorem**, 82 - **Cauchy–Riemann equations**, 32 - **chain of segments**, 16 - **circle**, 12 - **closed** - disk, 13 - path, 16 - **set**, 13 - **coffee**, 88, 132, 173 - **comparison test**, 127 - **complete**, 123 - **complex number**, 2 - **complex plane**, 5 - extended, 47 - **complex projective line**, 47 - **composition**, 27 - **concatenation**, 74 - **conformal**, 30, 44, 118 - **conjugate**, 10 - **connected**, 14 - **continuous**, 26 - **contractible**, 83 - **convergence**, 122 - **pointwise**, 131 - **uniform**, 131 #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 209 Context: # Table of Contents 1. **Convergence** - Sequence - Series - Cosine - Cotangent - Cross Ratio - Curve - Cycloid 2. **Numerical Concepts** - Dedekind Sum - Dense - Derivative - Partial - Difference Quotient - Differentiable - Dilation - Discriminant 3. **Geometric Concepts** - Disk - Closed - Open - Punctured - Unit - Distance of Complex Numbers - Divergent - Domain - Double Series 4. **Mathematical Constants** - e - Embedding of R into C - Empty Set - Entire Functions - Essential Singularity - Euclidean Plane - Euler’s Formula 5. **Functions and Theorems** - Even - Exponential Function - Exponential Rules - Extended Complex Plane - Fibonacci Numbers - Field - Fixed Point - Frobenius Problem - Functions - Conformal - Even - Exponential - Logarithmic - Odd - Trigonometric - Fundamental Theorem - Of Algebra - Of Calculus 6. **Applications** - Geogebra - Geometric Interpretation of Multiplication - Geometric Series - Group 7. **Harmonic Analysis** - Harmonic - Harmonic Conjugate - Holomorphic - Homotopy - Hyperbolic Trig Functions #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 210 Context: ``` # Index - i, 4 - identity, 3 - identity map, 23 - identity principle, 154 - image - of a function, 27 - of a point, 23 - imaginary axis, 5 - imaginary part, 4 - improper integral, 104, 186 - infinity, 46 - inside, 88 - integral, 71 - path independent, 102 - integral test, 129 - integration by parts, 92 - interior point, 13 - inverse function, 31 - of a Möbius transformation, 43 - inverse parametrization, 74 - inversion, 45 - isolated point, 13 - isolated singularity, 170 - Jacobian, 65 - Jordan curve theorem, 88 - L'Hôpital's rule, 197 - Laplace, 110 - Laurent series, 157 - least upper bound, 124, 137 - Leibniz's rule, 83, 196 - length, 73 - limit - infinity, 46 - of a function, 24 - of a sequence, 122 - of a series, 126 - linear fractional transformation, 43 - Liouville's theorem, 104 - Log, 59 - log, 61 - logarithm, 59 - logarithmic derivative, 180 - max/min property for harmonic functions, 115, 155 - maximum - strong relative, 115 - weak relative, 116, 155 - mean-value theorem - for harmonic functions, 114 - for holomorphic functions, 86 - for real functions, 195 - meromorphic, 181 - minimum - strong relative, 115 - weak relative, 155 - Möbius transformation, 43 - modulus, 5 - monotone, 124 - monotone sequence property, 124 - Morera's theorem, 100 - multiplication, 2 - north pole, 51 ``` #################### File: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf Page: 211 Context: ``` obvious, 23 odd, 167 one-to-one, 31 onto, 31 open disk, 12 set, 13 order of a pole, 173 orientation, 15 partial derivative, 32 path, 14 closed, 16 inside of, 88 interior of, 88 polygonal, 79 positively oriented, 88 path independent, 102 periodic, 55, 193 Picard's theorem, 174 piecewise smooth, 72 plane, 12 pointwise convergence, 131 Poisson integral formula, 119 Poisson kernel, 95, 118 polar form, 9 pole, 170 polynomial, 0, 20, 40, 102 positive orientation, 88 power series, 135 differentiation of, 147 integration of, 139 primitive, 76 primitive root of unity, 9 principal argument, 59 principal logarithm, 59 principal value of z, 61 punctured disk, 169 real axis, 5 real number, 2 real part, 4 rectangular form, 9 region, 14 of convergence, 136 simply-connected, 101, 111 removable singularity, 170 reparameterization, 73 residue theorem, 176 reverse triangle inequality, 11, 20 Riemann hypothesis, 130 Riemann sphere, 47 Riemann zeta function, 130 root, 4 root of unity, 9 root test, 138 Rouché's theorem, 182 separated, 14 sequence, 122 convergent, 122 divergent, 122 limit, 122 monotone, 124 series, 125 ``` ########## """QUERY: in 6 sentences what is complex numbers?""" Consider the chat history for relevant information. Use all information included. Use as much tokens as needed. Important: If you find information separated by a | in the context, it is a table formatted in Markdown.Important: Take a look at the QUERY and only the QUERY. If this is vague or unclear, please ignore everything and ask a follow-up question instead! Final Files Sources: A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 3, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 5, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 7, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 8, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 9, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 10, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 11, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 12, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 13, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 14, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 15, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 16, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 17, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 18, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 20, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 21, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 22, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 23, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 24, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 25, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 26, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 27, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 28, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 29, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 30, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 31, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 37, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 38, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 41, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 42, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 43, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 45, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 48, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 49, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 53, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 55, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 57, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 60, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 61, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 62, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 63, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 64, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 65, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 66, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 67, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 71, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 72, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 73, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 74, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 76, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 77, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 80, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 81, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 83, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 89, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 91, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 105, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 109, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 110, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 112, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 113, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 115, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 116, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 118, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 121, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 124, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 126, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 127, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 128, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 129, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 130, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 131, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 141, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 143, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 148, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 149, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 153, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 160, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 161, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 163, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 172, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 174, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 175, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 179, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 180, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 185, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 189, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 193, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 195, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 196, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 197, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 198, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 200, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 204, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 205, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 206, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 208, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 209, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 210, A%20First%20Course%20in%20Complex%20Analysis%20-%20Matthias%20Beck%2C%20Gerald%20Marchesi%2C%20Dennis%20Pixton%2C%20Lucas%20Sabalka%20%28PDF%29.pdf - Page 211 ================================================== **Elapsed Time: 6.17 seconds** ================================================== FINAL ANSWER Answer: Complex numbers are an extension of the real numbers, represented in the form \( z = x + iy \), where \( x \) is the real part, \( y \) is the imaginary part, and \( i \) is the imaginary unit defined by \( i^2 = -1 \). This formulation allows for the inclusion of solutions to equations that do not have real solutions, such as \( x^2 + 1 = 0 \). Complex numbers can be added, subtracted, multiplied, and divided (except by zero), following algebraic rules similar to those of real numbers, which include properties like commutativity and associativity. Geometrically, complex numbers can be visualized as points or vectors in a two-dimensional plane known as the complex plane, where the x-axis represents the real part and the y-axis represents the imaginary part. The introduction of complex numbers not only enriches the number system but also plays a crucial role in various fields of mathematics, physics, and engineering, particularly in solving polynomial equations and analyzing waveforms. Furthermore, every nonconstant polynomial has roots in the complex numbers, as stated by the Fundamental Theorem of Algebra, which asserts that the complex numbers are algebraically closed. ================================================== **Elapsed Time: 5.68 seconds** ==================================================