Lorenza Saitta, Attilio Giordana, Antoine CornuéjolsCambridge University Press, 6/16/2011EAN 9780521763912, ISBN10: 0521763916Hardcover, 410 pages, 25.4 x 19.6 x 2.8 cmLanguage: EnglishPhase 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.PrefaceAcknowledgementsNotation1. Introduction2. Statistical physics and phase transitions3. The satisfiability problem4. Constraint satisfaction problems5. Machine learning6. Searching the hypothesis space7. Statistical physics and machine learning8. Learning, SAT, and CSP9. Phase transition in FOL covering test10. Phase transitions and relational learning11. Phase transitions in grammatical inference12. Phase transitions in complex systems13. Phase transitions in natural systems14. Discussions and open issuesAppendix A. Phase transitions detected in two real casesAppendix B. An intriguing ideaReferencesIndex.
