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.

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

About the Author
Antoine Cornuejols is Full Professor of Computer Science at the AgroParisTech Engineering School in Paris. Attilio Giordana is Full Professor of Computer Science at the University of Piemonte Orientale in Italy. Lorenza Saitta is a Full Professor of Computer Science at the University of Piemonte Orientale in Italy.

Reviews
"... 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



Book Information
ISBN 9780521763912
Author Lorenza Saitta
Format Hardback
Page Count 410
Imprint Cambridge University Press
Publisher Cambridge University Press
Weight(grams) 1100g
Dimensions(mm) 254mm * 195mm * 27mm