Neural network design / Martin T. Hagan, Howard B. Demuth, Mark Hudson Beale and Orlando De Jesus

Includes index.

1. Introduction -- 2. Neuron Model and Network Architectures -- 3. An Illustrative Example -- 4. Perceptron Learning Role -- 5. Signal and Weight Vector Spaces -- 6. Linear Transformation 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. Generalization -- 14. Dynamic Networks -- 15. Competitive Networks -- 16. Radial Basis Networks -- 17. Practical Training Issues -- 18. Case Study: Function Approximation -- 19. Case Study 2: Probability Estimation -- 20. Case Study 3: Pattern Recognition -- 21. Case Study 4: Clustering -- 22. Case Study 5: Prediction -- Appendices

This book, by the authors of the Neural Network Toolbox for MATLAB, provides a clear and detailed coverage of fundamental neural network architectures and learning rules. In it, the authors emphasize a coherent presentation of the principal neural networks, methods for training them and their applications to practical problems.FeaturesExtensive coverage of training methods for both feedforward networks (including multilayer and radial basis networks) and recurrent networks. In addition to conjugate gradient and Levenberg-Marquardt variations of the backpropagation algorithm, the text also covers Bayesian regularization and early stopping, which ensure the generalization ability of trained networks.Associative and competitive networks, including feature maps and learning vector quantization, are explained with simple building blocks.A chapter of practical training tips for function approximation, pattern recognition, clustering and prediction, along with five chapters presenting detailed real-world case studies.Detailed examples and numerous solved problems.