This book provides clear and detailed coverage of fundamental neural network architectures and learning rules. In it, the authors emphasize a coherent presentation of the major neural networks, the methods for forming them and their applications to practical problems.
- Features Extensive coverage of training methods, both for forward power 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 building 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