The Handbook of Neural Computation is a practical, hands-on guide to the design and implementation of neural networks used by scientists and engineers to tackle difficult and/or time-consuming problems.
The handbook bridges an information pathway between scientists and engineers in different disciplines who apply neural networks to similar problems. It is unmatched in the breadth of its coverage and is certain to become the standard reference resource for the neural network community.
Table of Contents
Foreword by James A Anderson. Part A: Introduction. Part B: Fundamental concepts of neural computation. Part C: Neural network models. Part D: Hybrid models. Part E: Neural network implementations. Part F: Neural network applications. Part G: Neural networks in practice. Part H: Directions for future research. Part X: Appendices.
"One can be sure that any essential aspect of computation technology based on neural networks will be represented somewhere in this volume, greatly reducing the need to check numerous sources for relevant information. The quality of the writing and editing is outstanding, and the contents, which are based on recent results and experience of distinguished experts in the field, are very up-to-date. … the handbook constitutes a source of inspiration for practitioners and for experts in computational system applications whose value is hard to overestimate …"
"A wonderful concept well implemented in its initial stage, this handbook is both a place to start in neural networks and a place to grow with this dynamic field. I look forward to future additions of the same high quality and readability."
-H. John Caulfield
"Let me congratulate you on an excellent book-it will be of great value to the community of neural network researchers, and I find it invaluable."