Neural Networks: A Comprehensive Foundation, 2/E
0132733501

Simon Haykin, McMaster University, Ontario Canada

Publisher: Prentice Hall
Copyright: 1999
Format: Paper; 842 pp

ISBN-10: 0132733501
ISBN-13:9780132733502

Our Price: $150.00

Description

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.
Table Of Contents


 1. Introduction.


 2. Learning Processes.


 3. Single-Layer Perceptrons.


 4. Multilayer Perceptrons.


 5. Radial-Basis Function Networks.


 6. Support Vector Machines.


 7. Committee Machines.


 8. Principal Components Analysis.


 9. Self-Organizing Maps.


10. Information-Theoretic Models.


11. Stochastic Machines & Their Approximates Rooted in Statistical Mechanics.


12. Neurodynamic Programming.


13. Temporal Processing Using Feedforward Networks.


14. Neurodynamics.


15. Dynamically Driven Recurrent Networks.


Epilogue.


Bibliography.


Index.
Features
NEW TO THIS EDITION
  • NEW - New chapters now cover such areas as:

    • Support vector machines. Pg.___

    • Reinforcement learning/neurodynamic programming. Pg.___

    • Dynamically driven recurrent networks. Pg.___

  • NEW - End-of-chapter problems revised, improved and expanded in number. Detailed solutions manual to accompany the text. Pg.___
  • Extensive, state-of-the-art coverage exposes students to the many facets of neural networks and helps them appreciate the technology's capabilities and potential applications. Pg.___
  • Detailed analysis of back-propagation learning and multi-layer perceptrons. Pg.___
  • Explores the intricacies of the learning process—an essential component for understanding neural networks. Pg.___
  • 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 students the opportunity to see how neural networks are designed and perform in practice. Pg.___
  • Reinforces key concepts with chapter objectives, problems, worked examples, a bibliography, photographs, illustrations, and a thorough glossary. Pg.___
  • Includes a detailed and extensive bibliography for easy reference. Pg.___
  • Computer-oriented experiments distributed throughout the text.
  • Uses Matlab SE version 5.
New To This Edition
  • New chapters now cover such areas as:

    • Support vector machines. Pg.___

    • Reinforcement learning/neurodynamic programming. Pg.___

    • Dynamically driven recurrent networks. Pg.___

  • End-of-chapter problems revised, improved and expanded in number. Detailed solutions manual to accompany the text. Pg.___