D2L - Preface

https://d2l.ai/chapter_preface/index.html

Preface — Dive into Deep Learning 1.0.3 documentation

 

Preface

 

Just a few years ago, there were no legions of deep learning scientists developing intelligent products and services at major companies and startups. When we entered the field, machine learning did not command headlines in daily newspapers. Our parents had no idea what machine learning was, let alone why we might prefer it to a career in medicine or law. Machine learning was a blue skies academic discipline whose industrial significance was limited to a narrow set of real-world applications, including speech recognition and computer vision. Moreover, many of these applications required so much domain knowledge that they were often regarded as entirely separate areas for which machine learning was one small component. At that time, neural networks—the predecessors of the deep learning methods that we focus on in this book—were generally regarded as outmoded.

 

불과 몇 년 전만 해도 대기업과 스타트업에는 지능형 제품과 서비스를 개발하는 딥러닝 과학자 군단이 없었습니다. 우리가 현장에 들어갔을 때 머신러닝은 일간 신문의 헤드라인을 장식하지 않았습니다. 우리 부모님은 기계 학습이 무엇인지 전혀 몰랐고, 우리가 의학이나 법률 분야의 직업보다 기계 학습을 선호하는 이유도 몰랐습니다. 기계 학습은 산업적 중요성이 음성 인식 및 컴퓨터 비전을 포함한 좁은 실제 응용 프로그램 집합으로 제한되는 파란 하늘 학문 분야였습니다. 더욱이 이러한 응용 프로그램 중 다수에는 너무 많은 도메인 지식이 필요했기 때문에 기계 학습이 하나의 작은 구성 요소인 완전히 별도의 영역으로 간주되는 경우가 많았습니다. 그 당시에는 이 책에서 중점적으로 다루는 딥러닝 방법의 전신인 신경망이 일반적으로 시대에 뒤떨어진 것으로 간주되었습니다.

 

Yet in just few years, deep learning has taken the world by surprise, driving rapid progress in such diverse fields as computer vision, natural language processing, automatic speech recognition, reinforcement learning, and biomedical informatics. Moreover, the success of deep learning in so many tasks of practical interest has even catalyzed developments in theoretical machine learning and statistics. With these advances in hand, we can now build cars that drive themselves with more autonomy than ever before (though less autonomy than some companies might have you believe), dialogue systems that debug code by asking clarifying questions, and software agents beating the best human players in the world at board games such as Go, a feat once thought to be decades away. Already, these tools exert ever-wider influence on industry and society, changing the way movies are made, diseases are diagnosed, and playing a growing role in basic sciences—from astrophysics, to climate modeling, to weather prediction, to biomedicine.

 

그러나 불과 몇 년 만에 딥 러닝은 컴퓨터 비전, 자연어 처리, 자동 음성 인식, 강화 학습, 생물의학 정보학과 같은 다양한 분야에서 급속한 발전을 이루며 세상을 놀라게 했습니다. 더욱이, 실용적인 관심을 끄는 수많은 작업에서 딥 러닝의 성공은 이론적 기계 학습과 통계의 발전을 촉진하기도 했습니다. 이러한 발전을 통해 우리는 이제 그 어느 때보다 더 많은 자율성을 갖고 스스로 운전하는 자동차(일부 회사에 비해 자율성은 떨어지지만), 명확한 질문을 통해 코드를 디버깅하는 대화 시스템, 최고의 인간을 이기는 소프트웨어 에이전트를 만들 수 있습니다. 한때 수십 년이 걸릴 것으로 생각되었던 업적인 바둑과 같은 보드 게임에서 전 세계 플레이어가 게임을 즐기고 있습니다. 이미 이러한 도구는 영화 제작 방식, 질병 진단 방식을 변화시키고 천체 물리학에서 기후 모델링, 날씨 예측, 생물 의학에 이르기까지 기초 과학에서 점점 더 많은 역할을 수행하면서 산업과 사회에 더욱 광범위한 영향을 미치고 있습니다.

 

About This Book

 

This book represents our attempt to make deep learning approachable, teaching you the concepts, the context, and the code.

 

이 책은 딥 러닝을 접근하기 쉽게 만들고 개념, 맥락, 코드를 가르치려는 우리의 시도를 보여줍니다.

 

One Medium Combining Code, Math, and HTML

For any computing technology to reach its full impact, it must be well understood, well documented, and supported by mature, well-maintained tools. The key ideas should be clearly distilled, minimizing the onboarding time needed to bring new practitioners up to date. Mature libraries should automate common tasks, and exemplar code should make it easy for practitioners to modify, apply, and extend common applications to suit their needs.

 

모든 컴퓨팅 기술이 완전한 영향력을 발휘하려면 이를 잘 이해하고 문서화해야 하며 성숙하고 잘 관리되는 도구의 지원을 받아야 합니다. 핵심 아이디어는 명확하게 정리되어 새로운 실무자에게 최신 정보를 제공하는 데 필요한 온보딩 시간을 최소화해야 합니다. 성숙한 라이브러리는 일반적인 작업을 자동화해야 하며, 예시 코드를 통해 실무자는 필요에 따라 일반 애플리케이션을 쉽게 수정, 적용 및 확장할 수 있어야 합니다.

 

As an example, take dynamic web applications. Despite a large number of companies, such as Amazon, developing successful database-driven web applications in the 1990s, the potential of this technology to aid creative entrepreneurs was realized to a far greater degree only in the past ten years, owing in part to the development of powerful, well-documented frameworks.

 

예를 들어 동적 웹 애플리케이션을 살펴보겠습니다. 1990년대 아마존 등 수많은 기업이 데이터베이스 기반 웹 애플리케이션을 성공적으로 개발했음에도 불구하고,창의적 기업가를 지원하는 이 기술의 잠재력은 부분적으로 강력하고 잘 문서화된 프레임워크의 개발 덕분에 지난 10년 동안에야 훨씬 더 크게 실현되었습니다.

 

When we started this book project, there were no resources that simultaneously (i) remained up to date; (ii) covered the breadth of modern machine learning practices with sufficient technical depth; and (iii) interleaved exposition of the quality one expects of a textbook with the clean runnable code that one expects of a hands-on tutorial. We found plenty of code examples illustrating how to use a given deep learning framework (e.g., how to do basic numerical computing with matrices in TensorFlow) or for implementing particular techniques (e.g., code snippets for LeNet, AlexNet, ResNet, etc.) scattered across various blog posts and GitHub repositories. However, these examples typically focused on how to implement a given approach, but left out the discussion of why certain algorithmic decisions are made. While some interactive resources have popped up sporadically to address a particular topic, e.g., the engaging blog posts published on the website Distill, or personal blogs, they only covered selected topics in deep learning, and often lacked associated code. On the other hand, while several deep learning textbooks have emerged—e.g., Goodfellow et al. (2016), which offers a comprehensive survey on the basics of deep learning—these resources do not marry the descriptions to realizations of the concepts in code, sometimes leaving readers clueless as to how to implement them. Moreover, too many resources are hidden behind the paywalls of commercial course providers.

 

우리가 이 도서 프로젝트를 시작했을 때 동시에 (i) 최신 상태로 유지되는 리소스가 없었습니다. (ii) 충분한 기술적 깊이로 현대 기계 학습 사례의 폭을 다루었습니다. (iii) 실습 튜토리얼에서 기대하는 깔끔한 실행 가능 코드를 사용하여 교과서에서 기대하는 품질을 인터리브 방식으로 설명합니다. 우리는 주어진 딥 러닝 프레임워크를 사용하는 방법(예: TensorFlow에서 행렬을 사용하여 기본 수치 계산을 수행하는 방법) 또는 특정 기술을 구현하는 방법(예: LeNet, AlexNet, ResNet 등의 코드 조각)을 설명하는 많은 코드 예제를 발견했습니다. 다양한 블로그 게시물과 GitHub 저장소에 걸쳐 있습니다. 그러나 이러한 예는 일반적으로 주어진 접근 방식을 구현하는 방법에 중점을 두었지만 특정 알고리즘 결정이 내려지는 이유에 대한 논의는 생략했습니다. 특정 주제를 다루기 위해 일부 대화형 리소스(예: Distill 웹사이트에 게시된 매력적인 블로그 게시물 또는 개인 블로그)가 산발적으로 등장했지만 딥 러닝에서 선택된 주제만 다루었고 관련 코드가 부족한 경우가 많았습니다. 반면에 여러 딥러닝 교과서가 등장했지만(예: Goodfellow et al. (2016), 딥 러닝의 기본에 대한 포괄적인 조사를 제공합니다. 이러한 리소스는 설명과 코드의 개념 실현을 결합하지 않으며 때로는 독자가 이를 구현하는 방법에 대해 단서가 없게 만듭니다. 더욱이, 상업용 강좌 제공업체의 유료화벽 뒤에는 너무 많은 리소스가 숨겨져 있습니다.

 

We set out to create a resource that could (i) be freely available for everyone; (ii) offer sufficient technical depth to provide a starting point on the path to actually becoming an applied machine learning scientist; (iii) include runnable code, showing readers how to solve problems in practice; (iv) allow for rapid updates, both by us and also by the community at large; and (v) be complemented by a forum for interactive discussion of technical details and to answer questions.

 

우리는 (i) 모든 사람이 무료로 사용할 수 있는 리소스를 만들기 시작했습니다. (ii) 실제로 응용 기계 학습 과학자가 되기 위한 출발점을 제공하기에 충분한 기술적 깊이를 제공합니다. (iii) 실행 가능한 코드를 포함하여 독자에게 실제로 문제를 해결하는 방법을 보여줍니다. (iv) 당사와 커뮤니티 전반에 의한 신속한 업데이트를 허용합니다. (v) 기술 세부 사항에 대한 대화식 토론과 질문에 답변할 수 있는 포럼으로 보완됩니다.

 

These goals were often in conflict. Equations, theorems, and citations are best managed and laid out in LaTeX. Code is best described in Python. And webpages are native in HTML and JavaScript. Furthermore, we want the content to be accessible both as executable code, as a physical book, as a downloadable PDF, and on the Internet as a website. No workflows seemed suited to these demands, so we decided to assemble our own (Section 23.6). We settled on GitHub to share the source and to facilitate community contributions; Jupyter notebooks for mixing code, equations and text; Sphinx as a rendering engine; and Discourse as a discussion platform. While our system is not perfect, these choices strike a compromise among the competing concerns. We believe that Dive into Deep Learning might be the first book published using such an integrated workflow.

 

이러한 목표는 종종 충돌했습니다. 방정식, 정리 및 인용은 LaTeX에서 가장 잘 관리되고 배치됩니다. 코드는 Python에서 가장 잘 설명됩니다. 그리고 웹페이지는 HTML과 JavaScript로 기본 제공됩니다. 또한 우리는 콘텐츠가 실행 가능한 코드, 실제 책, 다운로드 가능한 PDF, 인터넷 웹사이트 모두에서 액세스할 수 있기를 원합니다. 이러한 요구 사항에 적합한 워크플로가 없어 보였으므로 자체적으로 구성하기로 결정했습니다(섹션 23.6). 우리는 소스를 공유하고 커뮤니티 기여를 촉진하기 위해 GitHub에 정착했습니다. 코드, 방정식 및 텍스트를 혼합하기 위한 Jupyter 노트북 렌더링 엔진으로서의 Sphinx; 토론 플랫폼으로서의 담론. 우리 시스템이 완벽하지는 않지만 이러한 선택은 경쟁하는 문제들 사이에서 타협점을 찾습니다. 우리는 Dive into Deep Learning이 이러한 통합 워크플로를 사용하여 출판된 최초의 책이 될 것이라고 믿습니다.

 

Learning by Doing

Many textbooks present concepts in succession, covering each in exhaustive detail. For example, the excellent textbook of Bishop (2006), teaches each topic so thoroughly that getting to the chapter on linear regression requires a nontrivial amount of work. While experts love this book precisely for its thoroughness, for true beginners, this property limits its usefulness as an introductory text.

 

많은 교과서에서는 각 개념을 철저하게 자세히 다루면서 개념을 연속적으로 제시합니다. 예를 들어, Bishop(2006)의 훌륭한 교과서는 각 주제를 너무 철저하게 가르치기 때문에 선형 회귀에 관한 장에 도달하려면 적지 않은 양의 작업이 필요합니다. 전문가들은 이 책의 철저함 때문에 좋아하지만, 진정한 초보자들에게는 입문용 텍스트로서의 유용성이 제한됩니다.

 

In this book, we teach most concepts just in time. In other words, you will learn concepts at the very moment that they are needed to accomplish some practical end. While we take some time at the outset to teach fundamental preliminaries, like linear algebra and probability, we want you to taste the satisfaction of training your first model before worrying about more esoteric concepts.

 

이 책에서 우리는 대부분의 개념을 적시에 가르칩니다. 즉, 실제적인 목적을 달성하기 위해 필요한 바로 그 순간에 개념을 배우게 됩니다. 선형 대수학 및 확률과 같은 기본 예비 과정을 가르치기 위해 처음에는 시간을 할애하지만, 더 난해한 개념에 대해 걱정하기 전에 첫 번째 모델 교육의 만족감을 맛보시기 바랍니다.

 

Aside from a few preliminary notebooks that provide a crash course in the basic mathematical background, each subsequent chapter both introduces a reasonable number of new concepts and provides several self-contained working examples, using real datasets. This presented an organizational challenge. Some models might logically be grouped together in a single notebook. And some ideas might be best taught by executing several models in succession. By contrast, there is a big advantage to adhering to a policy of one working example, one notebook: This makes it as easy as possible for you to start your own research projects by leveraging our code. Just copy a notebook and start modifying it.

 

기본 수학적 배경에 대한 단기 집중 강좌를 제공하는 몇 가지 예비 노트북 외에도 각 후속 장에서는 합리적인 수의 새로운 개념을 소개하고 실제 데이터 세트를 사용하여 몇 가지 독립적인 작업 예제를 제공합니다. 이는 조직적인 과제를 제시했습니다. 일부 모델은 논리적으로 단일 노트북에 함께 그룹화될 수 있습니다. 그리고 일부 아이디어는 여러 모델을 연속적으로 실행함으로써 가장 잘 배울 수 있습니다. 대조적으로, 하나의 작업 예제, 하나의 노트북 정책을 고수하면 큰 이점이 있습니다. 이를 통해 우리 코드를 활용하여 자신의 연구 프로젝트를 가능한 한 쉽게 시작할 수 있습니다. 노트북을 복사하고 수정을 시작하세요.

 

Throughout, we interleave the runnable code with background material as needed. In general, we err on the side of making tools available before explaining them fully (often filling in the background later). For instance, we might use stochastic gradient descent before explaining why it is useful or offering some intuition for why it works. This helps to give practitioners the necessary ammunition to solve problems quickly, at the expense of requiring the reader to trust us with some curatorial decisions.

 

전체적으로 우리는 필요에 따라 실행 가능한 코드를 배경 자료와 인터리브합니다. 일반적으로 우리는 도구를 완전히 설명하기 전에 도구를 사용 가능한 상태로 만드는 실수를 합니다(종종 나중에 배경을 채우는 경우가 많습니다). 예를 들어, 확률적 경사하강법이 왜 유용한지 설명하거나 작동하는 이유에 대한 직관을 제공하기 전에 확률적 경사하강법을 사용할 수 있습니다. 이는 독자가 일부 큐레이터 결정에 대해 우리를 신뢰하도록 요구하는 대신 실무자에게 문제를 신속하게 해결하는 데 필요한 수단을 제공하는 데 도움이 됩니다.

 

This book teaches deep learning concepts from scratch. Sometimes, we delve into fine details about models that would typically be hidden from users by modern deep learning frameworks. This comes up especially in the basic tutorials, where we want you to understand everything that happens in a given layer or optimizer. In these cases, we often present two versions of the example: one where we implement everything from scratch, relying only on NumPy-like functionality and automatic differentiation, and a more practical example, where we write succinct code using the high-level APIs of deep learning frameworks. After explaining how some component works, we rely on the high-level API in subsequent tutorials.

 

이 책은 딥러닝 개념을 처음부터 가르쳐줍니다. 때때로 우리는 최신 딥 러닝 프레임워크에 의해 일반적으로 사용자에게 숨겨지는 모델에 대한 세부 정보를 조사합니다. 이는 특히 특정 레이어나 옵티마이저에서 발생하는 모든 것을 이해하기를 원하는 기본 튜토리얼에서 나타납니다. 이러한 경우 우리는 종종 두 가지 버전의 예제를 제시합니다. 하나는 NumPy와 유사한 기능과 자동 차별화에만 의존하여 처음부터 모든 것을 구현하는 버전이고, 다른 하나는 고급 API를 사용하여 간결한 코드를 작성하는 보다 실용적인 예시입니다. 딥러닝 프레임워크. 일부 구성 요소의 작동 방식을 설명한 후 후속 자습서에서는 고급 API를 사용합니다.

 

Content and Structure

 

The book can be divided into roughly three parts, dealing with preliminaries, deep learning techniques, and advanced topics focused on real systems and applications (Fig. 1).

 

이 책은 대략 세 부분으로 나누어 실제 시스템과 애플리케이션에 초점을 맞춘 예비, 딥러닝 기법, 고급 주제를 다루고 있습니다(그림 1).

 

Fig. 1  Book structure.

 

• Part 1: Basics and Preliminaries. Section 1 is an introduction to deep learning. Then, in Section 2, we quickly bring you up to speed on the prerequisites required for hands-on deep learning, such as how to store and manipulate data, and how to apply various numerical operations based on elementary concepts from linear algebra, calculus, and probability. Section 3 and Section 5 cover the most fundamental concepts and techniques in deep learning, including regression and classification; linear models; multilayer perceptrons; and overfitting and regularization.

1부: 기초 및 예비. 섹션 1은 딥러닝에 대한 소개입니다. 그런 다음 2장에서는 데이터를 저장하고 조작하는 방법, 선형대수학, 미적분학, 미적분학 등의 기본 개념을 기반으로 다양한 수치 연산을 적용하는 방법 등 실습 딥러닝에 필요한 전제 조건을 빠르게 소개합니다. 그리고 확률. 섹션 3과 섹션 5에서는 회귀 및 분류를 포함하여 딥러닝의 가장 기본적인 개념과 기술을 다룹니다. 선형 모델; 다층 퍼셉트론; 그리고 과적합과 정규화.

 

• Part 2: Modern Deep Learning Techniques. Section 6 describes the key computational components of deep learning systems and lays the groundwork for our subsequent implementations of more complex models. Next, Section 7 and Section 8 present convolutional neural networks (CNNs), powerful tools that form the backbone of most modern computer vision systems. Similarly, Section 9 and Section 10 introduce recurrent neural networks (RNNs), models that exploit sequential (e.g., temporal) structure in data and are commonly used for natural language processing and time series prediction. In Section 11, we describe a relatively new class of models, based on so-called attention mechanisms, that has displaced RNNs as the dominant architecture for most natural language processing tasks. These sections will bring you up to speed on the most powerful and general tools that are widely used by deep learning practitioners.

2부: 최신 딥 러닝 기술. 섹션 6에서는 딥 러닝 시스템의 주요 계산 구성 요소를 설명하고 보다 복잡한 모델의 후속 구현을 위한 토대를 마련합니다. 다음으로 섹션 7과 섹션 8에서는 대부분의 최신 컴퓨터 비전 시스템의 백본을 형성하는 강력한 도구인 CNN(컨볼루션 신경망)을 소개합니다. 마찬가지로 섹션 9와 섹션 10에서는 데이터의 순차(예: 시간) 구조를 활용하고 자연어 처리 및 시계열 예측에 일반적으로 사용되는 모델인 순환 신경망(RNN)을 소개합니다. 섹션 11에서는 대부분의 자연어 처리 작업에 대한 지배적인 아키텍처로 RNN을 대체한 소위 attention 메커니즘을 기반으로 하는 상대적으로 새로운 클래스의 모델을 설명합니다. 이 섹션에서는 딥 러닝 실무자가 널리 사용하는 가장 강력하고 일반적인 도구를 빠르게 소개합니다.

 

• Part 3: Scalability, Efficiency, and Applications (available online). In Chapter 12, we discuss several common optimization algorithms used to train deep learning models. Next, in Chapter 13, we examine several key factors that influence the computational performance of deep learning code. Then, in Chapter 14, we illustrate major applications of deep learning in computer vision. Finally, in Chapter 15 and Chapter 16, we demonstrate how to pretrain language representation models and apply them to natural language processing tasks.

3부: 확장성, 효율성 및 애플리케이션(온라인으로 제공) 12장에서는 딥러닝 모델을 훈련하는 데 사용되는 몇 가지 일반적인 최적화 알고리즘에 대해 논의합니다. 다음으로 13장에서는 딥러닝 코드의 계산 성능에 영향을 미치는 몇 가지 핵심 요소를 살펴봅니다. 그런 다음 14장에서는 컴퓨터 비전에 딥러닝을 적용하는 방법을 설명합니다. 마지막으로 15장과 16장에서는 언어 표현 모델을 사전 훈련하고 이를 자연어 처리 작업에 적용하는 방법을 보여줍니다.

 

Code

Most sections of this book feature executable code. We believe that some intuitions are best developed via trial and error, tweaking the code in small ways and observing the results. Ideally, an elegant mathematical theory might tell us precisely how to tweak our code to achieve a desired result. However, deep learning practitioners today must often tread where no solid theory provides guidance. Despite our best attempts, formal explanations for the efficacy of various techniques are still lacking, for a variety of reasons: the mathematics to characterize these models can be so difficult; the explanation likely depends on properties of the data that currently lack clear definitions; and serious inquiry on these topics has only recently kicked into high gear. We are hopeful that as the theory of deep learning progresses, each future edition of this book will provide insights that eclipse those presently available.

 

이 책의 대부분의 섹션에는 실행 가능한 코드가 포함되어 있습니다. 우리는 시행착오를 통해 일부 직관이 가장 잘 개발되고, 코드를 작은 방식으로 조정하고 결과를 관찰한다고 믿습니다. 이상적으로, 우아한 수학 이론은 원하는 결과를 얻기 위해 코드를 조정하는 방법을 정확하게 알려줄 수 있습니다. 그러나 오늘날 딥 러닝 실무자들은 확실한 이론이 지침을 제공하지 않는 곳을 자주 밟아야 합니다. 최선의 노력에도 불구하고 다양한 기술의 효능에 대한 공식적인 설명은 여러 가지 이유로 여전히 부족합니다. 이러한 모델을 특성화하는 수학은 매우 어려울 수 있습니다. 설명은 현재 명확한 정의가 부족한 데이터의 속성에 따라 달라질 수 있습니다. 이러한 주제에 대한 진지한 조사는 최근에야 본격적으로 시작되었습니다. 우리는 딥러닝 이론이 발전함에 따라 이 책의 향후 버전이 현재 제공되는 통찰력을 능가하는 통찰력을 제공할 것이라는 희망을 갖고 있습니다.

 

To avoid unnecessary repetition, we capture some of our most frequently imported and used functions and classes in the d2l package. Throughout, we mark blocks of code (such as functions, classes, or collection of import statements) with #@save to indicate that they will be accessed later via the d2l package. We offer a detailed overview of these classes and functions in Section 23.8. The d2l package is lightweight and only requires the following dependencies:

 

불필요한 반복을 피하기 위해 가장 자주 가져오고 사용되는 함수와 클래스 중 일부를 d2l 패키지에 캡처합니다. 전체적으로 코드 블록(예: 함수, 클래스 또는 import 문 모음)을 #@save로 표시하여 나중에 d2l 패키지를 통해 액세스할 것임을 나타냅니다. 섹션 23.8에서 이러한 클래스와 함수에 대한 자세한 개요를 제공합니다. d2l 패키지는 경량이며 다음 종속성만 필요합니다.

 

#@save
import collections
import hashlib
import inspect
import math
import os
import random
import re
import shutil
import sys
import tarfile
import time
import zipfile
from collections import defaultdict
import pandas as pd
import requests
from IPython import display
from matplotlib import pyplot as plt
from matplotlib_inline import backend_inline

d2l = sys.modules[__name__]

 

Most of the code in this book is based on PyTorch, a popular open-source framework that has been enthusiastically embraced by the deep learning research community. All of the code in this book has passed tests under the latest stable version of PyTorch. However, due to the rapid development of deep learning, some code in the print edition may not work properly in future versions of PyTorch. We plan to keep the online version up to date. In case you encounter any problems, please consult Installation to update your code and runtime environment. Below lists dependencies in our PyTorch implementation.

 

이 책에 있는 대부분의 코드는 딥 러닝 연구 커뮤니티에서 열광적으로 수용한 인기 오픈 소스 프레임워크인 PyTorch를 기반으로 합니다. 이 책의 모든 코드는 PyTorch의 최신 안정 버전에서 테스트를 통과했습니다. 그러나 딥러닝의 급속한 발전으로 인해 인쇄판의 일부 코드가 향후 버전의 PyTorch에서 제대로 작동하지 않을 수 있습니다. 우리는 온라인 버전을 최신 상태로 유지할 계획입니다. 문제가 발생하는 경우 설치를 참조하여 코드와 런타임 환경을 업데이트하세요. 아래에는 PyTorch 구현의 종속성이 나열되어 있습니다.

 

#@save
import numpy as np
import torch
import torchvision
from PIL import Image
from scipy.spatial import distance_matrix
from torch import nn
from torch.nn import functional as F
from torchvision import transforms

 

Target Audience

This book is for students (undergraduate or graduate), engineers, and researchers, who seek a solid grasp of the practical techniques of deep learning. Because we explain every concept from scratch, no previous background in deep learning or machine learning is required. Fully explaining the methods of deep learning requires some mathematics and programming, but we will only assume that you enter with some basics, including modest amounts of linear algebra, calculus, probability, and Python programming. Just in case you have forgotten anything, the online Appendix provides a refresher on most of the mathematics you will find in this book. Usually, we will prioritize intuition and ideas over mathematical rigor. If you would like to extend these foundations beyond the prerequisites to understand our book, we happily recommend some other terrific resources: Linear Analysis by Bollobás (1999) covers linear algebra and functional analysis in great depth. All of Statistics (Wasserman, 2013) provides a marvelous introduction to statistics. Joe Blitzstein’s books and courses on probability and inference are pedagogical gems. And if you have not used Python before, you may want to peruse this Python tutorial.

 

이 책은 딥러닝의 실용적인 기술을 확실하게 이해하려는 학생(학부 또는 대학원), 엔지니어, 연구원을 위한 책입니다. 모든 개념을 처음부터 설명하기 때문에 딥 러닝이나 머신 러닝에 대한 사전 배경 지식이 필요하지 않습니다. 딥 러닝 방법을 완전히 설명하려면 약간의 수학과 프로그래밍이 필요하지만, 적당한 양의 선형 대수학, 미적분학, 확률 및 Python 프로그래밍을 포함한 몇 가지 기본 지식만 갖추고 있다고 가정합니다. 잊어버린 내용이 있을 경우를 대비해 온라인 부록을 통해 이 책에서 찾을 수 있는 대부분의 수학에 대해 다시 한 번 복습해 보세요. 일반적으로 우리는 수학적 엄격함보다 직관과 아이디어를 우선시합니다. 우리 책을 이해하기 위해 전제 조건 이상으로 이러한 기초를 확장하고 싶다면 다른 훌륭한 자료를 기꺼이 추천합니다. Bollobás의 선형 분석(1999)은 선형 대수학 및 함수 분석을 매우 깊이 다루고 있습니다. All of Statistics(Wasserman, 2013)는 통계에 대한 놀라운 소개를 제공합니다. 확률과 추론에 관한 Joe Blitzstein의 책과 강좌는 교육학적 보석입니다. 이전에 Python을 사용해 본 적이 없다면 이 Python 튜토리얼을 정독하는 것이 좋습니다.

 

Notebooks, Website, GitHub, and Forum

All of our notebooks are available for download on the D2L.ai website and on GitHub. Associated with this book, we have launched a discussion forum, located at discuss.d2l.ai. Whenever you have questions on any section of the book, you can find a link to the associated discussion page at the end of each notebook.

 

모든 노트북은 D2L.ai 웹사이트와 GitHub에서 다운로드할 수 있습니다. 이 책과 관련하여 우리는 토론 포럼(discuss.d2l.ai)을 시작했습니다. 책의 어떤 섹션에 대해 질문이 있을 때마다 각 노트북 끝에 있는 관련 토론 페이지에 대한 링크를 찾을 수 있습니다.

 

Acknowledgments

We are indebted to the hundreds of contributors for both the English and the Chinese drafts. They helped improve the content and offered valuable feedback. This book was originally implemented with MXNet as the primary framework. We thank Anirudh Dagar and Yuan Tang for adapting a majority part of earlier MXNet code into PyTorch and TensorFlow implementations, respectively. Since July 2021, we have redesigned and reimplemented this book in PyTorch, MXNet, and TensorFlow, choosing PyTorch as the primary framework. We thank Anirudh Dagar for adapting a majority part of more recent PyTorch code into JAX implementations. We thank Gaosheng Wu, Liujun Hu, Ge Zhang, and Jiehang Xie from Baidu for adapting a majority part of more recent PyTorch code into PaddlePaddle implementations in the Chinese draft. We thank Shuai Zhang for integrating the LaTeX style from the press into the PDF building.

 

우리는 영어와 중국어 초안 모두에 기여한 수백 명의 기고자들에게 빚을 지고 있습니다. 그들은 콘텐츠 개선에 도움을 주고 귀중한 피드백을 제공했습니다. 이 책은 원래 MXNet을 기본 프레임워크로 구현했습니다. 이전 MXNet 코드의 대부분을 각각 PyTorch 및 TensorFlow 구현에 적용한 Anirudh Dagar와 Yuan Tang에게 감사드립니다. 2021년 7월부터 우리는 PyTorch, MXNet, TensorFlow에서 이 책을 재설계하고 구현했으며 PyTorch를 기본 프레임워크로 선택했습니다. 최신 PyTorch 코드의 대부분을 JAX 구현에 적용한 Anirudh Dagar에게 감사드립니다. 최신 PyTorch 코드의 대부분을 중국 초안의 PaddlePaddle 구현에 적용한 Baidu의 Gaosheng Wu, Liujun Hu, Ge Zhang 및 Jiehang Xie에게 감사드립니다. 언론의 LaTeX 스타일을 PDF 건물에 통합한 Shuai Zhang에게 감사드립니다.

 

On GitHub, we thank every contributor of this English draft for making it better for everyone. Their GitHub IDs or names are (in no particular order): alxnorden, avinashingit, bowen0701, brettkoonce, Chaitanya Prakash Bapat, cryptonaut, Davide Fiocco, edgarroman, gkutiel, John Mitro, Liang Pu, Rahul Agarwal, Mohamed Ali Jamaoui, Michael (Stu) Stewart, Mike Müller, NRauschmayr, Prakhar Srivastav, sad-, sfermigier, Sheng Zha, sundeepteki, topecongiro, tpdi, vermicelli, Vishaal Kapoor, Vishwesh Ravi Shrimali, YaYaB, Yuhong Chen, Evgeniy Smirnov, lgov, Simon Corston-Oliver, Igor Dzreyev, Ha Nguyen, pmuens, Andrei Lukovenko, senorcinco, vfdev-5, dsweet, Mohammad Mahdi Rahimi, Abhishek Gupta, uwsd, DomKM, Lisa Oakley, Bowen Li, Aarush Ahuja, Prasanth Buddareddygari, brianhendee, mani2106, mtn, lkevinzc, caojilin, Lakshya, Fiete Lüer, Surbhi Vijayvargeeya, Muhyun Kim, dennismalmgren, adursun, Anirudh Dagar, liqingnz, Pedro Larroy, lgov, ati-ozgur, Jun Wu, Matthias Blume, Lin Yuan, geogunow, Josh Gardner, Maximilian Böther, Rakib Islam, Leonard Lausen, Abhinav Upadhyay, rongruosong, Steve Sedlmeyer, Ruslan Baratov, Rafael Schlatter, liusy182, Giannis Pappas, ati-ozgur, qbaza, dchoi77, Adam Gerson, Phuc Le, Mark Atwood, christabella, vn09, Haibin Lin, jjangga0214, RichyChen, noelo, hansent, Giel Dops, dvincent1337, WhiteD3vil, Peter Kulits, codypenta, joseppinilla, ahmaurya, karolszk, heytitle, Peter Goetz, rigtorp, Tiep Vu, sfilip, mlxd, Kale-ab Tessera, Sanjar Adilov, MatteoFerrara, hsneto, Katarzyna Biesialska, Gregory Bruss, Duy–Thanh Doan, paulaurel, graytowne, Duc Pham, sl7423, Jaedong Hwang, Yida Wang, cys4, clhm, Jean Kaddour, austinmw, trebeljahr, tbaums, Cuong V. Nguyen, pavelkomarov, vzlamal, NotAnotherSystem, J-Arun-Mani, jancio, eldarkurtic, the-great-shazbot, doctorcolossus, gducharme, cclauss, Daniel-Mietchen, hoonose, biagiom, abhinavsp0730, jonathanhrandall, ysraell, Nodar Okroshiashvili, UgurKap, Jiyang Kang, StevenJokes, Tomer Kaftan, liweiwp, netyster, ypandya, NishantTharani, heiligerl, SportsTHU, Hoa Nguyen, manuel-arno-korfmann-webentwicklung, aterzis-personal, nxby, Xiaoting He, Josiah Yoder, mathresearch, mzz2017, jroberayalas, iluu, ghejc, BSharmi, vkramdev, simonwardjones, LakshKD, TalNeoran, djliden, Nikhil95, Oren Barkan, guoweis, haozhu233, pratikhack, Yue Ying, tayfununal, steinsag, charleybeller, Andrew Lumsdaine, Jiekui Zhang, Deepak Pathak, Florian Donhauser, Tim Gates, Adriaan Tijsseling, Ron Medina, Gaurav Saha, Murat Semerci, Lei Mao, Levi McClenny, Joshua Broyde, jake221, jonbally, zyhazwraith, Brian Pulfer, Nick Tomasino, Lefan Zhang, Hongshen Yang, Vinney Cavallo, yuntai, Yuanxiang Zhu, amarazov, pasricha, Ben Greenawald, Shivam Upadhyay, Quanshangze Du, Biswajit Sahoo, Parthe Pandit, Ishan Kumar, HomunculusK, Lane Schwartz, varadgunjal, Jason Wiener, Armin Gholampoor, Shreshtha13, eigen-arnav, Hyeonggyu Kim, EmilyOng, Bálint Mucsányi, Chase DuBois, Juntian Tao, Wenxiang Xu, Lifu Huang, filevich, quake2005, nils-werner, Yiming Li, Marsel Khisamutdinov, Francesco “Fuma” Fumagalli, Peilin Sun, Vincent Gurgul, qingfengtommy, Janmey Shukla, Mo Shan, Kaan Sancak, regob, AlexSauer, Gopalakrishna Ramachandra, Tobias Uelwer, Chao Wang, Tian Cao, Nicolas Corthorn, akash5474, kxxt, zxydi1992, Jacob Britton, Shuangchi He, zhmou, krahets, Jie-Han Chen, Atishay Garg, Marcel Flygare, adtygan, Nik Vaessen, bolded, Louis Schlessinger, Balaji Varatharajan, atgctg, Kaixin Li, Victor Barbaros, Riccardo Musto, Elizabeth Ho, azimjonn, Guilherme Miotto, Alessandro Finamore, Joji Joseph, Anthony Biel, Zeming Zhao, shjustinbaek, gab-chen, nantekoto, Yutaro Nishiyama, Oren Amsalem, Tian-MaoMao, Amin Allahyar, Gijs van Tulder, Mikhail Berkov, iamorphen, Matthew Caseres, Andrew Walsh, pggPL, RohanKarthikeyan, Ryan Choi, and Likun Lei.

 

GitHub에서는 이 영어 초안을 모두에게 더 좋게 만들어 준 모든 기여자에게 감사드립니다. 해당 GitHub ID 또는 이름은 다음과 같습니다(특정 순서 없음):  alxnorden, avinashingit, bowen0701, brettkoonce, Chaitanya Prakash Bapat, cryptonaut, Davide Fiocco, edgarroman, gkutiel, John Mitro, Liang Pu, Rahul Agarwal, Mohamed Ali Jamaoui, Michael(Stu ) Stewart, Mike Müller, NRauschmayr, Prakhar Srivastav, sad-, sfermigier, Sheng Zha, sundeepteki, topecongiro, tpdi, vermicelli, Vishaal Kapoor, Vishwesh Ravi Shrimali, YaYaB, Yuhong Chen, Evgeniy Smirnov, lgov, Simon Corston-Oliver, Igor Dzreyev, Ha Nguyen, pmuens, Andrei Lukovenko, senorcinco, vfdev-5, dsweet, Mohammad Mahdi Rahimi, Abhishek Gupta, uwsd, DomKM, Lisa Oakley, Bowen Li, Aarush Ahuja, Prasanth Buddareddygari, brianhendee, mani2106, mtn, lkevinzc, caojilin , Lakshya, Fiete Lüer, Surbhi Vijayvargeeya, 김무현, dennismalmgren, adursun, Anirudh Dagar, liqingnz, Pedro Larroy, lgov, ati-ozgur, Jun Wu, Matthias Blume, Lin Yuan, geogunow, Josh Gardner, Maximilian Böther, Rakib Islam, Leonard Lausen, Abhinav Upadhyay, rongruosong, Steve Sedlmeyer, Ruslan Baratov, Rafael Schlatter, liusy182, Giannis Pappas, ati-ozgur, qbaza, dchoi77, Adam Gerson, Phuc Le, Mark Atwood, christabella, vn09, Haibin Lin, jjangga0214, RichyChen, noelo, hansent, Giel Dops, dvincent1337, WhiteD3vil, Peter Kulits, codypenta, joseppinilla, ahmaurya, karolszk, heytitle, Peter Goetz, rigtorp, Tiep Vu, sfilip, mlxd, Kale-ab Tessera, Sanjar Adilov, MatteoFerrara, hsneto, Katarzyna Biesialska , Gregory Bruss, Duy–Thanh Doan, paulaurel, greytowne, Duc Pham, sl7423, Jaedong Hwang, Yida Wang, cys4, clhm, Jean Kaddour, austinmw, trebeljahr, tbaums, Cuong V. Nguyen, pavelkomarov, vzlamal, NotAnotherSystem, J- Arun-Mani, jancio, eldarkurtic, the-great-shazbot, doctorcolossus, gducharme, clauss, Daniel-Mietchen, hoonose, biagiom, abhinavsp0730, jonathanhrandall, ysraell, Nodar Okroshiashvili, UgurKap, 강지양, StevenJokes, Tomer Kaftan, liweiwp, netyster , ypandya, NishantTharani, heiligerl, SportsTHU, Hoa Nguyen, manuel-arno-korfmann-webentwicklung, aterzis-personal, nxby, Xiaoting He, Josiah Yoder, mathresearch, mzz2017, jroberayalas, iluu, ghejc, BSharmi, vkramdev, simonwardjones, LakshKD, TalNeoran, djliden, Nikhil95, Oren Barkan, guoweis, haozhu233, pratikhack, Yue Ying, tayfununal, steinsag, charleybeller, Andrew Lumsdaine, Jiekui Zhang, Deepak Pathak, Florian Donhauser, Tim Gates, Adriaan Tijsseling, Ron Medina, Gaurav Saha, Murat Semerci , Lei Mao, Levi McClenny, Joshua Broyde, jake221, jonbally, zyhazwraith, Brian Pulfer, Nick Tomasino, Lefan Zhang, Hongshen Yang, Vinney Cavallo, yuntai, Yuanxiang Zhu, amarazov, pasricha, Ben Greenawald, Shivam Upadhyay, Quanshangze Du, Biswajit Sahoo, Parthe Pandit, Ishan Kumar, HomunculusK, Lane Schwartz, varadgunjal, Jason Wiener, Armin Gholampoor, Shreshtha13, eigen-arnav, 김형규, EmilyOng, Bálint Mucsányi, Chase DuBois, Juntian Tao, Wenxiang Xu, Lifu Huang, filevich, quake2005 , nils-werner, Yiming Li, Marsel Khisamutdinov, Francesco “Fuma” Fumagalli, Peilin Sun, Vincent Gurgul, qingfengtommy, Janmey Shukla, Mo Shan, Kaan Sancak, regob, AlexSauer, Gopalakrishna Ramachandra, Tobias Uelwer, Chao Wang, Tian Cao, Nicolas Corthorn, akash5474, kxxt, zxydi1992, Jacob Britton, Shuangchi He, zhmou, krahets, Jie-Han Chen, Atishay Garg, Marcel Flygare, adtygan, Nik Vaessen, 굵은 글씨체, Louis Schlessinger, Balaji Varatharajan, atgctg, Kaixin Li, Victor Barbaros , Riccardo Musto, Elizabeth Ho, azimjonn, Guilherme Miotto, Alessandro Finamore, Joji Joseph, Anthony Biel, Zeming Zhao, shjustinbaek, gab-chen, nantekoto, 니시야마 유타로, Oren Amsalem, Tian-MaoMao, Amin Allahyar, Gijs van Tulder, Mikhail Berkov, iamorphen, Matthew Caseres, Andrew Walsh, pggPL, RohanKarthikeyan, Ryan Choi 및 Likun Lei.

 

We thank Amazon Web Services, especially Wen-Ming Ye, George Karypis, Swami Sivasubramanian, Peter DeSantis, Adam Selipsky, and Andrew Jassy for their generous support in writing this book. Without the available time, resources, discussions with colleagues, and continuous encouragement, this book would not have happened. During the preparation of the book for publication, Cambridge University Press has offered excellent support. We thank our commissioning editor David Tranah for his help and professionalism.

 

Amazon Web Services, 특히 이 책을 집필하는 데 아낌없는 지원을 해주신 Wen-Ming Ye, George Karypis, Swami Sivasubramanian, Peter DeSantis, Adam Selipsky 및 Andrew Jassy에게 감사드립니다. 가용한 시간, 자원, 동료와의 토론, 지속적인 격려가 없었다면 이 책은 탄생하지 못했을 것입니다. 출판을 위한 책을 준비하는 동안 Cambridge University Press는 훌륭한 지원을 제공했습니다. 우리의 커미셔닝 편집자 David Tranah의 도움과 전문성에 감사드립니다.

 

Summary

Deep learning has revolutionized pattern recognition, introducing technology that now powers a wide range of technologies, in such diverse fields as computer vision, natural language processing, and automatic speech recognition. To successfully apply deep learning, you must understand how to cast a problem, the basic mathematics of modeling, the algorithms for fitting your models to data, and the engineering techniques to implement it all. This book presents a comprehensive resource, including prose, figures, mathematics, and code, all in one place.

 

딥 러닝은 컴퓨터 비전, 자연어 처리, 자동 음성 인식 등 다양한 분야에서 광범위한 기술을 지원하는 기술을 도입하여 패턴 인식에 혁명을 일으켰습니다. 딥러닝을 성공적으로 적용하려면 문제를 캐스팅하는 방법, 모델링의 기본 수학, 모델을 데이터에 맞추는 알고리즘, 그리고 이를 모두 구현하는 엔지니어링 기술을 이해해야 합니다. 이 책은 산문, 그림, 수학, 코드를 포함한 포괄적인 리소스를 한 곳에서 제공합니다.

 

Exercises

 

1. Register an account on the discussion forum of this book discuss.d2l.ai.
   이 책 Discuss.d2l.ai의 토론 포럼에 계정을 등록하세요.
   
   
2. Install Python on your computer.
   컴퓨터에 Python을 설치합니다.
   
   
3. Follow the links at the bottom of the section to the forum, where you will be able to seek out help and discuss the book and find answers to your questions by engaging the authors and broader community.
   섹션 하단에 있는 포럼 링크를 따라가면 도움을 받을 수 있고 책에 대해 토론할 수 있으며 저자 및 더 넓은 커뮤니티에 참여하여 질문에 대한 답변을 찾을 수 있습니다.