Principal component neural networks : theory and applications / K.I. Diamantaras, S.Y. Kung.
"Systematically explores the relationship between principal component analysis (PCA) and neural networks. Provides a synergistic examination of the mathematical, algorithmic, application and architectural aspects of principal component neural networks. Using a unified formulation, the authors p...
Saved in:
Main Authors: | , |
---|---|
Format: | Book |
Language: | English |
Published: |
New York :
Wiley,
[1996]
|
Series: | Adaptive and learning systems for signal processing, communications, and control.
|
Subjects: | |
Online Access: | Contributor biographical information |
Table of Contents:
- Preface
- 1. Introduction
- 2. A Review of Linear Algebra
- 3. Principal Component Analysis
- 4. PCA Neural Networks
- 5. Channel Noise and Hidden Units
- 6. Heteroassociative Models
- 7. Signal Enhancement Against Noise
- 8. VLSI Implementation
- Appendix A Stochastic Approximation
- Appendix B Derivatives with Vectors and Matrices
- Appendix C Compactness and Convexity
- Bibliography
- Index.