Foundations of Machine Learning – Second Edition

Foundations of Machine Learning provides a comprehensive introduction to machine learning, suitable as a graduate level textbook or as a reference book for researchers. The book develops the foundations of theory and conceptual tools necessary to understand and justify machine learning algorithms, while covering the core concepts and modern topics in the field. It also discusses practical issues such as using these algorithms.

Table of Contents

• Introduction
• The PAC Learning Framework
• Rademacher Complexity and VC-Dimension
• Model Selection
• Support Vector Machines
• Kernel Methods
• Boosting
• On-Line Learning
• Multi-Class Classification
• Ranking
• Regression
• Maximum Entropy Models
• Conditional Maximum Entropy Models
• Algorithmic Stability
• Dimensionality Reduction
• Learning Automata and Languages
• Reinforcement Learning

Download Free PDF / Read Online