加载中...

SUPPORT

觉得内容有帮助？请站长喝杯咖啡 ☕

网站所有内容免费，但运维不免费 😭 AI、服务器、域名……你的支持将用来维持网站正常运行，让这个小站还能继续写下去~

微信赞助收款二维码

打开微信扫一扫 · 金额随意

首页知识库教程工具博客资讯术语表面试题库关于?个人中心

← 返回课程

动手学深度学习

155 / 189·markdown

Preface

01Preface

Installation

02Installation

Notation

03Notation

Introduction

04Introduction

Preliminaries

05Preliminaries
06Data Manipulation
07Data Preprocessing
08Linear Algebra
09Calculus
10Automatic Differentiation
11Probability and Statistics
12Documentation

Linear Neural Networks for Regression

13Linear Neural Networks for Regression
14Linear Regression
15Object-Oriented Design for Implementation
16Synthetic Regression Data
17Linear Regression Implementation from Scratch
18Concise Implementation of Linear Regression
19Generalization
20Weight Decay

Linear Neural Networks for Classification

21Linear Neural Networks for Classification
22Softmax Regression
23The Image Classification Dataset
24The Base Classification Model
25Softmax Regression Implementation from Scratch
26Concise Implementation of Softmax Regression
27Generalization in Classification
28Environment and Distribution Shift

Multilayer Perceptrons

29Multilayer Perceptrons
30Multilayer Perceptrons
31Implementation of Multilayer Perceptrons
32Forward Propagation, Backward Propagation, and Computational Graphs
33Numerical Stability and Initialization
34Generalization in Deep Learning
35Dropout
36Predicting House Prices on Kaggle

Builders' Guide

37Builders' Guide
38Layers and Modules
39Parameter Management
40Parameter Initialization
41Lazy Initialization
42Custom Layers
43File I/O
44GPUs

Convolutional Neural Networks

45Convolutional Neural Networks
46From Fully Connected Layers to Convolutions
47Convolutions for Images
48Padding and Stride
49Multiple Input and Multiple Output Channels
50Pooling
51Convolutional Neural Networks (LeNet)

Modern Convolutional Neural Networks

52Modern Convolutional Neural Networks
53Deep Convolutional Neural Networks (AlexNet)
54Networks Using Blocks (VGG)
55Network in Network (NiN)
56Multi-Branch Networks (GoogLeNet)
57Batch Normalization
58Residual Networks (ResNet) and ResNeXt
59Densely Connected Networks (DenseNet)
60Designing Convolution Network Architectures

Recurrent Neural Networks

61Recurrent Neural Networks
62Working with Sequences
63Converting Raw Text into Sequence Data
64Language Models
65Recurrent Neural Networks
66Recurrent Neural Network Implementation from Scratch
67Concise Implementation of Recurrent Neural Networks
68Backpropagation Through Time

Modern Recurrent Neural Networks

69Modern Recurrent Neural Networks
70Long Short-Term Memory (LSTM)
71Gated Recurrent Units (GRU)
72Deep Recurrent Neural Networks
73Bidirectional Recurrent Neural Networks
74Machine Translation and the Dataset
75The Encoder--Decoder Architecture
76Sequence-to-Sequence Learning for Machine Translation
77Beam Search

Attention Mechanisms and Transformers

78Attention Mechanisms and Transformers
79Queries, Keys, and Values
80Attention Pooling by Similarity
81Attention Scoring Functions
82The Bahdanau Attention Mechanism
83Multi-Head Attention
84Self-Attention and Positional Encoding
85The Transformer Architecture
86Transformers for Vision
87Large-Scale Pretraining with Transformers

Optimization Algorithms

88Optimization Algorithms
89Optimization and Deep Learning
90Convexity
91Gradient Descent
92Stochastic Gradient Descent
93Minibatch Stochastic Gradient Descent
94Momentum
95Adagrad
96RMSProp
97Adadelta
98Adam
99Learning Rate Scheduling

Computational Performance

100Computational Performance
101Compilers and Interpreters
102Asynchronous Computation
103Automatic Parallelism
104Hardware
105Training on Multiple GPUs
106Concise Implementation for Multiple GPUs
107Parameter Servers

Computer Vision

108Computer Vision
109Image Augmentation
110Fine-Tuning
111Object Detection and Bounding Boxes
112Anchor Boxes
113Multiscale Object Detection
114The Object Detection Dataset
115Single Shot Multibox Detection
116Region-based CNNs (R-CNNs)
117Semantic Segmentation and the Dataset
118Transposed Convolution
119Fully Convolutional Networks
120Neural Style Transfer
121Image Classification (CIFAR-10) on Kaggle
122Dog Breed Identification (ImageNet Dogs) on Kaggle

Natural Language Processing: Pretraining

123Natural Language Processing: Pretraining
124Word Embedding (word2vec)
125Approximate Training
126The Dataset for Pretraining Word Embeddings
127Pretraining word2vec
128Word Embedding with Global Vectors (GloVe)
129Subword Embedding
130Word Similarity and Analogy
131Bidirectional Encoder Representations from Transformers (BERT)
132The Dataset for Pretraining BERT
133Pretraining BERT

Natural Language Processing: Applications

134Natural Language Processing: Applications
135Sentiment Analysis and the Dataset
136Sentiment Analysis: Using Recurrent Neural Networks
137Sentiment Analysis: Using Convolutional Neural Networks
138Natural Language Inference and the Dataset
139Natural Language Inference: Using Attention
140Fine-Tuning BERT for Sequence-Level and Token-Level Applications
141Natural Language Inference: Fine-Tuning BERT

Reinforcement Learning

142Reinforcement Learning
143Markov Decision Process (MDP)
144Value Iteration
145Q-Learning

Gaussian Processes

146Gaussian Processes
147Introduction to Gaussian Processes
148Gaussian Process Priors
149Gaussian Process Inference

Hyperparameter Optimization

150Hyperparameter Optimization
151What Is Hyperparameter Optimization?
152Hyperparameter Optimization API
153Multi-Fidelity Hyperparameter Optimization
154Asynchronous Successive Halving

Generative Adversarial Networks

155Generative Adversarial Networks
156Generative Adversarial Networks
157Deep Convolutional Generative Adversarial Networks

Recommender Systems

158Recommender Systems
159Overview of Recommender Systems
160The MovieLens Dataset
161Matrix Factorization
162AutoRec: Rating Prediction with Autoencoders
163Personalized Ranking for Recommender Systems
164Neural Collaborative Filtering for Personalized Ranking
165Sequence-Aware Recommender Systems
166Feature-Rich Recommender Systems
167Factorization Machines
168Deep Factorization Machines

Appendix: Mathematics for Deep Learning

169Appendix: Mathematics for Deep Learning
170Geometry and Linear Algebraic Operations
171Eigendecompositions
172Single Variable Calculus
173Multivariable Calculus
174Integral Calculus
175Random Variables
176Maximum Likelihood
177Distributions
178Naive Bayes
179Statistics
180Information Theory

Appendix: Tools for Deep Learning

181Appendix: Tools for Deep Learning
182Using Jupyter Notebooks
183Using Amazon SageMaker
184Using AWS EC2 Instances
185Using Google Colab
186Selecting Servers and GPUs
187Contributing to This Book
188Utility Functions and Classes
189The d2l API Document

Chapter 155

Generative Adversarial Networks

Generative Adversarial Networks

toc

:maxdepth: 2

gan
dcgan

上一章

Asynchronous Successive Halving

下一章

Generative Adversarial Networks

本页镜像自上游仓库，固定版本 23d7a5ae。许可证：需人工确认。原文只读，笔记与划线保存在你的助记词身份下。

阅读进度

0%

整课进度0/189 章 · 0%

快捷键：←/→ 换章 · C 完成 · F 专注 · Esc 退出

阅读设置

字号

行宽

行距

本章笔记

选中正文可划线或写笔记。随助记词身份同步，仅自己可见。

暂无笔记。选中一段文字试试。

本章导航

中文 AI 学习与实践平台。知识库、教程、工具与资讯集中一站，帮你把人工智能真正学到手。

联系support.aimaster.cc@gmail.com

意见反馈 · 内容纠错 · 需求交流

探索

知识库
教程
工具
博客
资讯
术语表
面试题库
关于我们
隐私政策
服务条款

专题

精选教程
机器学习
深度学习
自然语言处理
计算机视觉

© 2026 AI Master. All rights reserved.

隐私政策·服务条款·关于我们·精通人工智能 · ai-master.cc