Deep Learning with Python: Based on TensorFlow

Name: Deep Learning with Python: Based on TensorFlow
ISBN: 9787111609728

吴茂贵 / 王冬 / 李涛 / Yang BenfaChina Machine Press2018

No rating yet

Chapters: 26
Series: Intelligent Systems and Technology Series
ISBN: 9787111609728

Report an error Find this book

Summary

Co-authored by Wu Maogui, Wang Dong, Li Tao and Yang Benfa, all with hands-on experience in big data and artificial intelligence, this book is a practical guide to deep learning for beginners. It is organized in three progressive layers—fundamentals, theory, and applications and extensions—and runs to 22 chapters in three parts. Part One (Chapters 1–5) covers the Python and applied mathematics foundations: common NumPy operations and broadcasting, Theano as an early deep learning framework, tensor operations and eigenvalue decomposition in linear algebra, the basics of probability and information theory, and probabilistic graphical models, clearing away mathematical and tooling obstacles for what follows. Part Two (Chapters 6–20) covers deep learning theory and applications and forms the main body of the book. It begins with machine learning fundamentals and the challenges of deep learning and how to address them, then explains installing and using TensorFlow on CPU and GPU, and goes on to cover image processing, neuron functions, autoencoders, Word2Vec, convolutional neural networks, recurrent neural networks and TensorFlow's high-level wrappers, with integrated hands-on cases such as sentiment analysis, breast cancer prediction, chatbots and face recognition. Part Three (Chapters 21–22) is supplementary, briefly introducing the basics of reinforcement learning and generative adversarial networks. The book uses diagrams alongside a large amount of runnable code and emphasizes understanding and getting code to run; it serves both as a systematic introduction for beginners and as a reference for readers with some machine learning background who need to build up their TensorFlow engineering skills.

Editor's review

第一，这本书的写法很照顾初学者。它不急着把读者推进公式里，而是从NumPy、Theano、线性代数、概率与信息论一路铺到机器学习基础，层层铺垫，数学底子一般的人也能跟下来。第二，内容选择比较“全栈”。它不只讲模型原理，还讲TensorFlow的安装、建模、图像处理、神经元函数、自编码器、CNN、RNN、高层封装，最后落到情感分析、乳腺癌预测、聊天机器人、人脸识别等综合案例，让读者能把知识点串成一条完整的动手链路。第三，作者都来自工程一线。吴茂贵在BI与数据挖掘领域有二十余年经验，其他几位分别在工业大数据、人工智能项目和算法工程上有多年的实践，因此书里的很多取舍更偏向“实际能怎么用”。第四点需要提前说明：本书2018年出版，代码围绕TensorFlow 1.x时代的API展开，与现在的TensorFlow 2.x/Keras或PyTorch写法有较大差异。作为理解深度学习原理与经典网络结构的中文读物它依然有价值，但读者最好把它当“原理与历史实践”来读，动手时主动对照新版本文档迁移代码。

Who it's for

A good fit for

刚学完Python、想系统入门深度学习的在校学生与自学者
有机器学习基础、需要补齐TensorFlow工程能力的数据从业者
需要讲解神经网络与CNN/RNN结构的中小学高校教师与培训讲师
想通过完整案例理解图像分类、NLP、人脸识别流程的技术管理者

Not a good fit for

已熟练使用TensorFlow 2.x或PyTorch，追求最新API的资深算法工程师
希望直接学习大模型、扩散模型等当下前沿方法的读者
完全没有编程基础、也没有线性代数与概率基础的纯新手

Reading tips

第一部分不必逐页精读，先用NumPy与线性代数章节标出自己没把握的概念，带着问题进入后面章节。
动手前先确认本机TensorFlow版本，书中1.x写法在新版上多处需改写，建议边读边对照官方文档迁移。
每读完一章网络结构，至少跑通一个书中案例并试着改超参数，观察损失曲线的变化。
把第17～20章的案例当作课程作业，自己重新组织数据与训练流程，比抄代码收获更大。

About the publisher

China Machine Press China · Founded in 1950

In addition to science and technology and professional publishing, the books in our catalog from China Machine Press also reflect a sustained focus on psychology, computing, management, finance and economics, and social sciences. In psychology, the catalog includes works by C. G. Jung and introductions to analytical psychology, as well as applied topics such as stress and health, and addiction and healing. In computing, it features Structure and Interpretation of Computer Programs (JavaScript Edition). Management and finance titles include Administrative Behavior (4th Edition), The Price of Inequality (Collector's Edition), and This Time Is Different: Eight Centuries of Financial Folly (Commemorative Edition). In the philosophy and history of science, there is The Worldview: The Third Edition. Relevant authors include C. G. Jung, William McGuire, Sonu Shamdasani, and Gabor Maté. Public information is limited; the above summarizes the publisher's profile based solely on the books in our catalog.

Preface
Part One Foundations of Python and Applied Mathematics
Chapter 1 Common NumPy Operations
Chapter 2 Theano Basics
Chapter 3 Linear Algebra
Chapter 4 Probability and Information Theory
Chapter 5 Probabilistic Graphical Models
Part Two Deep Learning Theory and Applications
Chapter 6 Machine Learning Fundamentals
Chapter 7 Challenges and Strategies of Deep Learning
Chapter 8 Installing TensorFlow
Chapter 9 TensorFlow Basics
Chapter 10 Image Processing with TensorFlow
Chapter 11 Neuron Functions in TensorFlow
Chapter 12 Autoencoders in TensorFlow
Chapter 13 Word2Vec with TensorFlow
Chapter 14 Convolutional Neural Networks with TensorFlow
Chapter 15 Recurrent Neural Networks with TensorFlow
Chapter 16 High-Level Wrappers in TensorFlow
Chapter 17 Sentiment Analysis
Chapter 18 Breast Cancer Prediction with TensorFlow
Chapter 19 Chatbots
Chapter 20 Face Recognition
Part Three Extensions
Chapter 21 Reinforcement Learning Basics
Chapter 22 Generative Adversarial Networks

FAQ

这本书的代码还能直接运行吗？

书中代码基于2018年前后的TensorFlow 1.x版本，包括会话、占位符等写法。在TensorFlow 2.x上不能直接运行，需要按新API改写，或安装旧版本环境配合阅读，建议以理解原理为主。

需要什么样的数学基础？

书中第一部分专门梳理了线性代数、概率与信息论、概率图模型。具备本科工科数学水平即可，若基础薄弱可先通读该部分，不必推导每个公式。

它和同名书籍《Python深度学习》（肖莱著）是一本吗？

不是。肖莱所著《Python深度学习》由人民邮电出版社出版，以Keras为主；本书为吴茂贵等四位作者著、机械工业出版社出版，以TensorFlow为主，两书内容与作者均不同。

书里的实战案例有哪些？

根据可核实的目录，第二部分包含情感分析、利用TensorFlow预测乳腺癌、聊天机器人、人脸识别四个综合案例，另配有信用卡欺诈检测、图像处理等示例。

有没有第2版？

有。机械工业出版社于2022年推出第2版，ISBN 9787111712244，全书调整为20章，内容按新版TensorFlow重写，并加入注意力机制、目标检测、生成式深度学习等章节。

Comments

Find this book

This site is an index: you start “Search all sources” in your browser, and the entries it lists all point to third-party sites; please judge their availability yourself.

About the author

吴茂贵 Author

Wu Maogui — public information about this author is limited, and no authoritative account of their identity or background is available. Their writing direction can nonetheless be inferred from the two works held in the collection, both in computing and artificial intelligence: AIGC Principles and Practice: Learning Large Language Models, Diffusion Models, and Multimodal Models from Scratch, and From Python Basics to AI in Practice. The first introduces generative AI to beginners, explaining the principles of large language models, diffusion models, and multimodal models while guiding readers through hands-on practice; the second starts from Python and gradually moves toward applied artificial intelligence. Both emphasize a path from fundamentals to practical work, using accessible language suited to readers without prior background. Wu Maogui's writing thus tends to break complex technologies into actionable introductory material, combining conceptual explanation with exercises for newcomers to the field.

王冬 Author

Wang Dong is a Chinese author whose works span a notably wide range of subjects. Public information about him is limited, and details of his life—such as nationality, dates of birth and death, education, and professional experience—cannot be confirmed. Judging from the seven works held in the collection, his writing touches on military studies, engineering technology, computing, social science, personal finance, and design. These include an edition of classical military writings, textbooks such as Engineering Fluid Mechanics (2nd Edition) and University Computer Science: Computation and Intelligence, a social-science look at the United States in Seeing America, and a finance title on how top investors profit from world history. He has also contributed to a vocational logistics textbook on warehouse management and a practical guide to e-commerce design. Overall, his writing combines knowledge popularization with instructional practicality and covers a broad range of readers' needs.

李涛 Author

Li Tao is an author whose works span a wide range of fields, with 27 titles held in the collection. The subjects he writes on are notably diverse: medical professional titles such as Clinical Psychopathology and the National County-Level Hospital Practical Handbook series volume Psychiatrist's Handbook, as well as clinical technical topics like Minimally Invasive Surgery for Diabetic Retinopathy; education and social issues in The Modernization of Chinese Rural Education; and practical tutorials on software and computing, including Adobe After Effects CC: The Master's Path. He has also written on science popularization and legal thinking, such as Perfect Symmetry: The Accidental Discovery of Fullerenes and 50 Lessons on Cultivating Citizens' Legal Thinking: Think Like a Lawyer, and contributed to applied writing such as the Technical Guidelines for Evaluating Healthy Enterprise Development. Because public information is limited, his personal biography, professional background, and identity remain unclear; from the distribution of his works, one can only see that he combines specialized writing with popular outreach, reaching readers in medicine, education, software, popular science, and law.