Phase Transitions in Machine Learning

This state-of-the-art overview of the field describes how phase transitions occur and teaches appropriate methods for tackling the consequent problems.

Lorenza Saitta (Author), Attilio Giordana (Author), Antoine Cornuéjols (Author)

9780521763912, Cambridge University Press

Hardback, published 16 June 2011

410 pages, 90 b/w illus. 10 tables
25.4 x 19.5 x 2.7 cm, 1.1 kg

"... it is still an open question whether this will be one of the basic tools for understanding machine learning problems and methods in the future. Naturally, this book is an essential source for researchers who want to find answers to these questions."
Joe Hernandez-Orallo, Computing Reviews

Phase transitions typically occur in combinatorial computational problems and have important consequences, especially with the current spread of statistical relational learning as well as sequence learning methodologies. In Phase Transitions in Machine Learning the authors begin by describing in detail this phenomenon, and the extensive experimental investigation that supports its presence. They then turn their attention to the possible implications and explore appropriate methods for tackling them. Weaving together fundamental aspects of computer science, statistical physics and machine learning, the book provides sufficient mathematics and physics background to make the subject intelligible to researchers in AI and other computer science communities. Open research issues are also discussed, suggesting promising directions for future research.

Preface
Acknowledgements
Notation
1. Introduction
2. Statistical physics and phase transitions
3. The satisfiability problem
4. Constraint satisfaction problems
5. Machine learning
6. Searching the hypothesis space
7. Statistical physics and machine learning
8. Learning, SAT, and CSP
9. Phase transition in FOL covering test
10. Phase transitions and relational learning
11. Phase transitions in grammatical inference
12. Phase transitions in complex systems
13. Phase transitions in natural systems
14. Discussions and open issues
Appendix A. Phase transitions detected in two real cases
Appendix B. An intriguing idea
References
Index.

Subject Areas: Machine learning [UYQM]