Neural Networks Design – Martin T. Hagan – 2nd Edition


This provides clear and detailed coverage of fundamental neural architectures and rules. In it, the authors emphasize a coherent presentation of the major neural networks, the for forming them and their applications to practical .

  • Features Extensive coverage of training methods, both for forward networks (including multiple layers and radial base networks) and recurrent networks.
  • In addition to the conjugate gradient and Levenberg-Marquardt’s backward propagation algorithm, the text also covers Bayesian regularization and early stopping, which ensure the generalization ability of trained networks.
  • Associative and competitive networks, which include feature maps and vector quantization learning, are explained by simple blocks.
  • A chapter of practical training tips for the approach function, pattern recognition, grouping and prediction, along with five chapters that present detailed case studies

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. Further Reading.

Inline Feedbacks
View all comments
Would love your thoughts, please comment.x