本书《机器学习：算法视角（第2版）》系统地介绍了机器学习的核心理论与实用技术，通过丰富的实例和算法解析，帮助读者深入理解并掌握机器学习的精髓。
Title: Machine Learning: An Algorithmic Perspective, 2nd Edition
Author: Stephen Marsland
Length: 457 pages
Edition: 2
Language: English
Publisher: Chapman and Hall/CRCPublication Date: October 8, 2014
ISBN-10: 1466583282
ISBN-13: 9781466583283
This book offers a practical approach for students with limited statistical knowledge to understand machine learning algorithms. Since the first edition was published, there have been significant developments in the field of machine learning, particularly concerning the statistical interpretation of these algorithms.
The second edition includes two new chapters on deep belief networks and Gaussian processes. It also reorganizes content for a more natural flow and revises material on support vector machines with an implementation provided for experimentation. Additional topics covered include random forests, perceptron convergence theorem, accuracy methods, conjugate gradient optimization for multi-layer perceptrons, Kalman filters, particle filters, and improved Python code.
The book is suitable as both an introductory one-semester course textbook and a more advanced study guide. It encourages students to practice with the provided examples and includes detailed problems in each chapter. All of the example code used throughout the text can be accessed on the authors website.
Table of Contents:
1. Introduction
2. Preliminaries
3. Neurons, Neural Networks, and Linear Discriminants
4. The Multi-layer Perceptron
5. Radial Basis Functions and Splines
6. Dimensionality Reduction
7. Probabilistic Learning
8. Support Vector Machines
9. Optimization and Search
10. Evolutionary Learning
11. Reinforcement Learning
12. Learning with Trees
13. Decision by Committee: Ensemble Learning
14. Unsupervised Learning
15. Markov Chain Monte Carlo (MCMC) Methods
16. Graphical Models
17. Symmetric Weights and Deep Belief Networks
18. Gaussian Processes
5星
