Machine Learning Methods
Description
In an era where artificial intelligence (AI) is transforming every industry, mastering a core set of machine learning methods is essential for both understanding and applying modern AI technologies. Machine Learning Method (Second Edition) stands out as a rigorously structured, method-oriented guide that systematically presents the most foundational and widely used techniques across four key branches: supervised learning, unsupervised learning, deep learning, and reinforcement learning.
This open access book is featured with its clear organization around algorithmic methods-such as GBDT, EM algorithm, Transformer, diffusion models, and PPO-that have remained central to machine learning despite rapid advancements in the field. Through concise mathematical formulations, intuitive explanations, and practical examples, the book offers deep insights into over 80 essential techniques. Each volume provides a focused overview, followed by chapters that explicate one or two key methods, making the content accessible for comprehensive study or targeted reference.
Designed for advanced undergraduate and graduate students, educators, and AI professionals, this book serves both as a textbook and a long-term reference. It assumes foundational knowledge in calculus, linear algebra, probability, and computer science, and rewards readers with a structured understanding of machine learning that is both theoretical and application-ready. Whether you're curious about why Transformers revolutionized NLP, or how PPO optimizes decision-making in reinforcement learning, this book will not only inform but also inspire further exploration.
More details
Other editions
Previous edition
Persons
Hang Li is a recognized authority in machine learning, natural language processing, and information retrieval. A Fellow of the Association for Computational Linguistics, ACM, and IEEE, he is also a Distinguished Member of the China Computer Federation. Dr. Li holds a Ph.D. in Computer Science from the University of Tokyo and began his career as a researcher at NEC Corporation. He later advanced to senior roles as a Research Manager at Microsoft Research Asia, Director of Huawei Noah's Ark Lab, Director of ByteDance AI Lab, and Head of Research at ByteDance.
He has authored more than 160 papers in premier conferences and journals, including NeurIPS, ICML, ACL, SIGIR, and JMLR, and has served on the editorial boards and program committees of many leading venues in these fields. Dr. Li is also a recipient of the CCF-ACM AI Award and several Best Paper awards, and he holds more than 60 U.S. patents related to real-world AI applications. He has contributed to the development of influential products such as Microsoft SharePoint and Jinri Toutiao.
His book, Statistical Learning Methods, is widely known as the "Blue Bible" of machine learning in China, and the present volume builds on this legacy by offering a comprehensive, method-driven perspective on core machine learning technologies. Known for his precision in theory and clarity in writing, Dr. Li brings both depth and accessibility to the study of machine learning.
Content
Volume I Supervised Learning.- Chapter 1 Introduction to Machine Learning.- Chapter 2 Introduction to Supervised Learning.- Chapter 3 Linear Regression.- Chapter 4 Perceptron.- Chapter 5 K -Nearest Neighbors.- Chapter 6 The Naïve Bayes Method.- Chapter 7 Decision Trees.- Chapter 8 Logistic Regression and Maximum Entropy Models.- Chapter 9 Support Vector Machines.- Chapter 10 Boosting.- Chapter 11 Hidden Markov Models.- Chapter 12 Conditional Random Fields.- Chapter 13 Summary of Supervised Learning Methods.- Volume II Unsupervised Learning.- Chapter 14 Introduction to Unsupervised Learning.- Chapter 15 Clustering Methods.- Chapter 16 Singular Value Decomposition.- Chapter 17 Principal Component Analysis.- Chapter 18 EM Algorithm and Variational EM Algorithm.- Chapter 19 Markov Chain Monte Carlo Methods.- Chapter 20 Latent Semantic Analysis and Non-negative Matrix Factorization.- Chapter 21 Probabilistic Latent Semantic Analysis.- Chapter 22 Latent Dirichlet Allocation.- Chapter 23 Summary of Unsupervised Learning Methods.- Volume III Deep Learning.- Chapter 24 Introduction to Deep Learning.- Chapter 25 Feedforward Neural Networks.- Chapter 26 Convolutional Neural Networks.- Chapter 27 Recurrent Neural Networks.- Chapter 28 Transformer.- Chapter 29 GPT and BERT.- Chapter 30 Variational Autoencoder.- Chapter 31 Generative Adversarial Networks.- Chapter 32 Diffusion Models.- Chapter 33 Summary of Deep Learning Methods.- Volume IV Reinforcement Learning.- Chapter 34 Introduction to Reinforcement Learning.- Chapter 35 Markov Decision Processes.- Chapter 36 Multi-Armed Bandits.- Chapter 37 Value-Based Methods.- Chapter 38 Deep Q-Networks.- Chapter 39 Policy-Based Methods.- Chapter 40 Proximal Policy Optimization (PPO).- Chapter 41 Summary of Reinforcement Learning Methods.