For graduate-level neural network courses offered in the departments of Computer Engineering, Electrical Engineering, and Computer Science.
Renowned for its thoroughness and readability, this well-organized and completely up-to-date text remains the most comprehensive treatment of neural networks from an engineering perspective. Thoroughly revised.
Renowned for its thoroughness and readability, this well-organized and completely up-to-date text remains the most comprehensive treatment of neural networks from an engineering perspective. Thoroughly revised.
 NEW TO THIS EDITION 
   - NEW—New chapters now cover such areas as:  - Support vector machines. 
- Reinforcement learning/neurodynamic programming. 
- Dynamically driven recurrent networks. 
- NEW-End—of-chapter problems revised, improved and expanded in number. 
 FEATURES - Extensive, state-of-the-art coverage exposes the reader to the many facets of neural networks and helps them appreciate the technology's capabilities and potential applications. 
- Detailed analysis of back-propagation learning and multi-layer perceptrons. 
- Explores the intricacies of the learning process—an essential component for understanding neural networks. 
- Considers recurrent networks, such as Hopfield networks, Boltzmann machines, and meanfield theory machines, as well as modular networks, temporal processing, and neurodynamics. 
- Integrates computer experiments throughout, giving the opportunity to see how neural networks are designed and perform in practice. 
- Reinforces key concepts with chapter objectives, problems, worked examples, a bibliography, photographs, illustrations, and a thorough glossary. 
- Includes a detailed and extensive bibliography for easy reference. 
- Computer-oriented experiments distributed throughout the book 
- Uses Matlab SE version 5.