Information-Theoretic Approach to Neural Computing

Name: Information-Theoretic Approach to Neural Computing
Price: 37.2 USD
Availability: InStock
ISBN: 9780387946665

ISBN-10: 0387946667

ISBN-13: 9780387946665

Edition: 1996

Authors: Gustavo Deco, Dragan Obradovic

List price: $129.00

30 day, 100% satisfaction guarantee!

Marketplace

2 new & used from $37.20

what's this?

Rush Rewards U
Members Receive:

You have reached 400 XP and carrot coins. That is the daily max!

Description:

Neural networks provide a powerful new technology to model and control nonlinear and complex systems. In this book, the authors present a detailed formulation of neural networks from the information-theoretic viewpoint. They show how this perspective provides new insights into the design theory of neural networks. In particular they show how these methods may be applied to the topics of supervised and unsupervised learning including feature extraction, linear and non-linear independent component analysis, and Boltzmann machines. Readers are assumed to have a basic understanding of neural networks, but all the relevant concepts from information theory are carefully introduced and explained.…

Book details

List price: $129.00
Copyright year: 1996
Publisher: Springer
Publication date: 9/5/1997
Binding: Hardcover
Pages: 262
Size: 6.50" wide x 9.75" long x 0.75" tall
Weight: 1.298
Language: English



Acknowledgments


Foreword



Introduction



Preliminaries of Information Theory and Neural Networks



Linear Feature Extraction: Infomax Principle



Independent Component Analysis: General Formulation and Linear Case



Nonlinear Feature Extraction: Boolean Stochastic Networks



Nonlinear Feature Extraction: Deterministic Neural Networks



Supervised Learning and Statistical Estimation



Statistical Physics Theory of Supervised Learning and Generalization



Composite Networks



Information Theory Based Regularizing Methods


References


Index