Machine Learning (English Version)

Author: Tom M. Mitchell
Publisher:
Publication Date: 2003-03-01
Features: Machine learning is the study of computer algorithms that can automatically improve through experience. Its applications range from data mining programs to information filtering systems, and even to automated tools, which are already very extensive. Machine learning has absorbed achievements and concepts from many disciplines, including artificial intelligence, probability theory and mathematical statistics, philosophy, information theory, biology, cognitive science, and control theory, to understand the context of problems, algorithms, and implicit assumptions in algorithms. This book presents the core algorithms and theories in machine learning and clarifies the operation of the algorithms. It primarily covers various practical theories and algorithms in machine learning, including concept learning, decision trees, neural networks, Bayesian learning, instance-based learning, genetic algorithms, rule learning, explanation-based learning, and reinforcement learning. For each topic, the author not only provides detailed and intuitive explanations but also offers practical algorithmic workflows. This book has been used as a textbook for machine learning courses by many universities, such as Carnegie Mellon. This book presents the core algorithms and theories in machine learning and clarifies the application of the algorithms. It primarily covers various practical theories and algorithms in machine learning, including concept learning, decision trees, neural networks, Bayesian learning, instance-based learning, genetic algorithms, rule learning, explanation-based learning, and reinforcement learning. For each topic, the author not only provides detailed and intuitive explanations but also offers practical algorithmic workflows. This book has been used as a textbook for machine learning courses by many universities, such as Carnegie Mellon.