Neural Network Learning: Theoretical Foundations [Hardcover]

Martin Anthony (Author), Peter L. Bartlett (Author)

Book Description

ISBN-10: 052157353X | ISBN-13: 978-0521573535 | Publication Date: November 13, 1999 | Edition: 1

This important work describes recent theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. Chapters survey research on pattern classification with binary-output networks, including a discussion of the relevance of the Vapnik Chervonenkis dimension, and of estimates of the dimension for several neural network models. In addition, Anthony and Bartlett develop a model of classification by real-output networks, and demonstrate the usefulness of classification with a "large margin." The authors explain the role of scale-sensitive versions of the Vapnik Chervonenkis dimension in large margin classification, and in real prediction. Key chapters also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient, constructive learning algorithms. The book is self-contained and accessible to researchers and graduate students in computer science, engineering, and mathematics.

Editorial Reviews

Review

"This book gives a thorough but nevertheless self-contained treatment of neural network learning from the perspective of computational learning theory." Mathematical Reviews

"This book is a rigorous treatise on neural networks that is written for advanced graduate students in computer science. Each chapter has a bibliographical section with helpful suggestions for further reading...this book would be best utilized within an advanced seminar context where the student would be assisted with examples, exercises, and elaborative comments provided by the professor." Telegraphic Reviews

Book Description

This book describes recent theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. The authors also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient constructive learning algorithms. The book is essentially self-contained, since it introduces the necessary background material on probability, statistics, combinatorics and computational complexity; and it is intended to be accessible to researchers and graduate students in computer science, engineering, and mathematics.

Product Details

• Hardcover: 403 pages
• Publisher: Cambridge University Press; 1 edition (November 13, 1999)
• Language: English
• ISBN-10: 052157353X
• ISBN-13: 978-0521573535
• Product Dimensions: 9.2 x 6.2 x 1 inches
• Shipping Weight: 1.5 pounds (View shipping rates and policies)
• Average Customer Review: 5.0 out of 5 stars  See all reviews (1 customer review)
• Amazon Best Sellers Rank: #3,281,593 in Books (See Top 100 in Books)

More About the Author

Discover books, learn about writers, read author blogs, and more.

Customer Reviews

Most Helpful Customer Reviews

22 of 73 people found the following review helpful:

5.0 out of 5 stars Amazing! Awesome! Staggering!, June 28, 1999

By A Customer

This review is from: Neural Network Learning: Theoretical Foundations (Hardcover)

A stonking blockbuster of a book, filled with raw power and suspense! From the heart stopping narrative on the on the Need for Conditions on the Activation Functions, to the torrid account of Classes of Finite Pseudo-dimension, this is truly the most exhilarating and disturbing description yet of the mathematical foundations of machine learning. I eagerly await the sequel.