Mark Hudson Beale
President

Home > Products > Neural Network Design Textbook

By Martin T. Hagan, Howard B. Demuth and Mark Hudson Beale

Neural Network Design provides a clear and detailed survey of basic neural network architectures and learning rules. In it, the authors emphasize mathematical analysis of networks, methods for training networks, and application of networks to practical engineering problems in pattern recognition, signal processing, and control systems.

The book incorporates necessary background material (such as linear algebra, optimization, and stability), while including extensive coverage of performance learning, like the Widrow-Hoff rule and back propogation. The authors introduce several enhancements of the most popular training method, back propogation, such as the conjugate gradient and Levenberg-Marquardt variations.

The text is an excellent purchase for anyone interested in how neural networks work, getting the most out of the Neural Network Toolbox, or wanting to research better neural network algorithms.

Table of Contents
1. Introduction
2. Neuron Model and Network Architectures
3. An Illustrative Example
4. Perceptron Learning Rule
5. Signal and Weight Vector Spaces
6. Linear Transformations for Neural Networks
7. Supervised Hebbian Learning
8. Performance Surfaces and Optimum Points
9. Performance Optimization
10. Widrow-Hoff Learning
11. Backpropagation
12. Variations on Backpropagation
13. Associative Learning
14. Competitive Networks
15. Grossberg Network
16. Adaptive Resonance Theory
17. Stability
18. Hopfield Network
19. Epilogue

Purchasing

Used versions of the text from Amazon.com.
(http://www.amazon.com/exec/obidos/ASIN/0534943322/mhbinc/102-4162343-8560135)

You can purchase new versions from Colorado State University here. (no link yet)

Downloadable Resources

Classroom transparency masters. (no link yet)

57 graphical demos for the Neural Network Toolbox. (no link yet)