An Information-Theoretic Approach to Neural Computing /
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 n...
| Main Author: | |
|---|---|
| Corporate Author: | |
| Other Authors: | |
| Format: | eBook |
| Language: | English |
| Published: |
New York, NY :
Springer New York,
1996.
|
| Series: | Perspectives in neural computing.
|
| Subjects: | |
| Online Access: | Connect to the full text of this electronic book |
Table of Contents:
- 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.