谷歌研究员Kevin Patrick Murphy撰写的经典机器学习图书，由MIT出版社出版，《Machine Learning: a Probabilistic Perspective》，自2012年发行以来就奉为经典机器学习书目。本书内容完整，讲解详细，便于阅读，方便工程使用。最近作者在Github上发布了关于本书的Python代码


http://people.cs.ubc.ca/~murphyk/MLbook/

目录

Chapter 1: 引言 Introduction
Chapter 2: 概率 Probability
Chapter 3: 面向离散数据的生成式模型 Generative models for discrete data
Chapter 4: 高斯模型 Gaussian models
Chapter 5: 贝叶斯统计 Bayesian statistics
Chapter 6: 频率统计 Frequentist statistics
Chapter 7: 线性回归 Linear regression
Chapter 8: 逻辑回归 Logistic regression
Chapter 9: 广义线性模型和指数族 Generalized linear models and the exponential family
Chapter 10: 有向图模型(贝叶斯网络) Directed graphical models (Bayes nets)
Chapter 11: 混合模型与EM算法 Mixture models and the EM algorithm
Chapter 12: 隐式线性模型 Latent linear models
Chapter 13: 稀疏线性模型 Sparse linear models
Chapter 14: 核方法 Kernels
Chapter 15: 高斯过程 Gaussian processes
Chapter 16: 自适应基函数模型 Adaptive basis function model
Chapter 17: 马尔可夫模型和隐马尔可夫模型 Markov and hidden Markov Models
Chapter 18: 状态空间模型 State space models
Chapter 19: 无向图模型(马尔可夫随机域) Undirected graphical models (Markov random fields)
Chapter 20: 图模型精准推断 Exact inference algorithms for graphical models
Chapter 21: 变分推断 Variational inference
Chapter 22: 更进变分推断 More variational inference
Chapter 23: 蒙特卡洛推断 Monte Carlo inference algorithms
Chapter 24: 马尔科夫链蒙特卡洛推断 MCMC inference algorithms
Chapter 25: 聚类 Clustering
Chapter 26: 图模型结构学习 Graphical model structure learning
Chapter 27: 因变量 Latent variable models for discrete data
Chapter 28: 深度学习 Deep learning


《机器学习:概率视角》第二版的Python 3代码
https://github.com/probml/pyprobml