我喜欢书,对于搞到的每一本机器学习书籍,我都要去读。

我认为,有好的参考资源,是对你心中机器学习谜题进行“解惑”的最快方式。阅读多本书,你就有了看待疑难问题的多种角度。

这份指南中,你会发现机器学习领域最值得一读的好书。

有许多原因促使人们想要机器学习书籍。因此,我采用了三种不同方式对机器学习书籍进行分类、排列,使读者们能按图索骥快速查找。比方说:

依据类别(难易):教材,科普等。

依据话题:Python,深度学习等

依据出版商:Packt,O’Reilly 等

如何使用这份指南?

找到一个你最感兴趣的话题

浏览所选类别的书目

购书、借书、下载

从头读到尾

重复以上过程

把书摆在家里、办公室显眼的地方,跟你读过那本书是两码事。别瞎搞收藏。

1.0 依据难易水平

1.1 机器学习科普读物

这是面向普通大众的机器学习书目。它们让你体会到机器学习和数据科学的优点和益处,但免去了理论和应用细节。我还加入了一些个人非常喜欢的、偏“统计思维”的流行科普读物。

The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World

译本:终极算法:机器学习和人工智能如何重塑世界

Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die

译本:大数据预测

The Signal and the Noise: Why So Many Predictions Fail–but Some Don't

Naked Statistics: Stripping the Dread from the Data

The Drunkard's Walk: How Randomness Rules Our Lives

该类别的首选是: The Signal and the Noise

20170125 01 learning02

与上述读物的乐观相比,提供了反面观点的是:Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy.

1.2 初学者书籍

真正面向零基础初学者的机器学习书籍,基本上是一片市场空白。下面的这些书,既包含了科普读物(见 1.1)中使用机器学习的益处,也部分包含了多见于入门书籍(见 1.3)的应用细节。

Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking

Data Smart: Using Data Science to Transform Information into Insight

Data Mining: Practical Machine Learning Tools and Techniques (第四版)

译本:数据挖掘:实用机器学习工具与技术(第三版)

Doing Data Science: Straight Talk from the Frontline

译本:数据科学实战 

该类别的首选是:Data Mining: Practical Machine Learning Tools and Techniques (数据挖掘:实用机器学习工具与技术)

20170125 01 learning03

1.3 机器学习入门书籍

下面是菜鸟入门的首选书单。相当于本科生级别的机器学习资源,适合基础学习者以及开发者新手。它们覆盖了广泛的机器学习话题,倾向于“怎么做”,而非“为什么”或是探讨理论。

Machine Learning for Hackers: Case Studies and Algorithms to Get You Started

译本:机器学习:实用案例解析 

Machine Learning in Action

译本:机器学习实战 

Programming Collective Intelligence: Building Smart Web 2.0 Applications

译本:集体智慧编程 

An Introduction to Statistical Learning: with Applications in R

译本:统计学习导论:基于R应用 

Applied Predictive Modeling

译本:应用预测建模

该类别的首选是:An Introduction to Statistical Learning: with Applications in R (统计学习导论:基于R应用)

20170125 01 learning04

1.4 (国外)机器学习教科书

下面是世界一流机器学习教材的列表。这些是研究生课程中会使用到的教科书,覆盖了一系列方法和背后的理论。

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

译本:统计学习基础:数据挖掘、推理与预测

Pattern Recognition and Machine Learning

Machine Learning: A Probabilistic Perspective

Learning From Data

Machine Learning

Machine Learning: The Art and Science of Algorithms that Make Sense of Data

译本:机器学习

Foundations of Machine Learning

该类别的首选是: The Elements of Statistical Learning: Data Mining, Inference, and Prediction (统计学习基础:数据挖掘、推理与预测)

20170125 01 learning05

2.0 依据话题

2.1 与R语言相关

R语言平台的应用机器学习书目。

R for Data Science: Import, Tidy, Transform, Visualize, and Model Data

Machine Learning with R

Machine Learning With R Cookbook – 110 Recipes for Building Powerful Predictive Models with R

国内名为:R语言机器学习参考手册(英文影印版)

R Machine Learning By Example

R Machine Learning Essentials

Mastering Machine Learning with R

An Introduction to Statistical Learning: with Applications in R

译本:统计学习导论:基于R应用 

Practical Data Science with R

译本:数据科学:理论、方法与R语言实践

Applied Predictive Modeling

译本:应用预测建模

R and Data Mining: Examples and Case Studies

译本:计算机科学丛书:R语言与数据挖掘最佳实践和经典案例

该类别的首选是:Applied Predictive Modeling(应用预测建模)

20170125 01 learning06

2.2 与Python相关

使用Python或SciPy语言平台的应用机器学习书目。

Python Machine Learning

国内名为:Python 语言构建机器学习系统(英文影印版)

Data Science from Scratch: First Principles with Python

译本:数据科学入门 (图灵程序设计丛书)

Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques for Building Intelligent Systems

Introduction to Machine Learning with Python: A Guide for Data Scientists

Vital Introduction to Machine Learning with Python: Best Practices to Improve and Optimize Machine Learning Systems and Algorithms

Machine Learning in Python: Essential Techniques for Predictive Analysis 

译本:Python机器学习:预测分析核心算法 

Python Data Science Handbook: Essential Tools for Working with Data

Introducing Data Science: Big Data, Machine Learning, and more, using Python tools

Real-World Machine Learning

该类别的首选是: Python Machine Learning (Python 语言构建机器学习系统)

20170125 01 learning07

2.3 深度学习

深度学习书目。现在没几本深度学习的好书,所以我只得用数量弥补质量。其中有许多专门针对 Tesnorflow 的教程。雷锋网注:该类推荐书目“全军覆没”——没有一本书有中文译本。这或许是因为深度学习领域理论框架尚不完善,缺乏影响力巨大的著作。

Deep Learning

Deep Learning: A Practitioner's Approach

Fundamentals of Deep Learning: Designing Next-Generation Machine Intelligence Algorithms

Learning TensorFlow: A guide to building deep learning systems

Machine Learning with TensorFlow

TensorFlow Machine Learning Cookbook

Getting Started with TensorFlow

TensorFlow for Machine Intelligence: A Hands-On Introduction to Learning Algorithms

该类别毫无疑问的首选是:Deep Learning.

20170125 01 learning08

另外,Michael Nielsen的免费电子书Neural Networks and Deep Learning简单易懂,深受许多入门学习者的喜爱。

2.4 时间序列预测

时间序列预测领域最值得一读的书目。在该技术的应用方面,目前R语言是霸主。

Time Series Analysis: Forecasting and Control

Practical Time Series Forecasting with R: A Hands-On Guide

Introduction to Time Series and Forecasting

Forecasting: principles and practice

该类别的入门首选是:Forecasting: principles and practice.

20170125 01 learning09

该类别的首选教材是:Time Series Analysis: Forecasting and Control.

20170125 01 learning10

3.0 依据出版商

有三个出版商在机器学习领域下了大力气,并且在认真出版图书。

它们是: O'Reilly, Manning和Packt。它们的焦点是应用书籍。该榜单上的书籍质量参差不齐:从严谨设计、编排的图书到装订在一起的博文。

3.1 O'Reilly 机器学习书籍

在它们的“数据”类别,O'Reilly有超过100本图书,许多与机器学习相关。以下是最畅销的几本:

Programming Collective Intelligence: Building Smart Web 2.0 Applications

译本:集体智慧编程

Introduction to Machine Learning with Python: A Guide for Data Scientists

Deep Learning: A Practitioner's Approach

Fundamentals of Deep Learning: Designing Next-Generation Machine Intelligence Algorithms

Data Science from Scratch: First Principles with Python

译本:数据科学入门

Python Data Science Handbook: Essential Tools for Working with Data

这些书中,Programming Collective Intelligence: Building Smart Web 2.0 Applications(集体智慧编程) 或许是开创了O'Reilly该目录的书,一直很受欢迎。

20170125 01 learning11

3.2 Manning机器学习书籍

Manning的书偏实用,并且质量还行,虽然数量没O’Reilly和Packt那么多。

Machine Learning in Action

译本:机器学习实战

Real-World Machine Learning

Introducing Data Science: Big Data, Machine Learning, and more, using Python tools

Practical Data Science with R

译本:数据科学:理论、方法与R语言实践

Manning 目录里较突出的一本是 Machine Learning in Action(机器学习实战),这也许同样是因为,它是该出版社在机器学习和数据科学领域的第一本出版物。

20170125 01 learning12

3.3 Packt 机器学习书籍

感觉上Packt全面拥抱了数据科学和机器学习领域的图书出版。他们有一大堆针对晦涩难懂机器学习库的书。在流行话题上面,比如R和Python,也有不少书籍出版。注:可惜的是,Packt似乎不重视汉语市场,旗下主要机器学习图书并没有中文译本。

以下是一些较流行的书目:

Machine Learning with R

Python Machine Learning

Practical Machine Learning

Machine Learning in Java

Mastering .NET Machine Learnin

(本文来源于雷锋网)