Cover image for Neural networks and fuzzy systems : a dynamical systems approach to machine intelligence
Title:
Neural networks and fuzzy systems : a dynamical systems approach to machine intelligence
Personal Author:
Publication Information:
Englewood Cliffs, NJ : Prentice-Hall, 1992
Physical Description:
2 computer disks; 5 1/4 in
ISBN:
9780136114352
General Note:
Accompanies text of the same title by the same author

Available:*

Library
Item Barcode
Call Number
Material Type
Item Category 1
Status
Searching...
30000002137176 DSK 463 j1n2 Open Access Computer File Diskette (Open Shelves)
Searching...
Searching...
30000002137192 DSK 463 j2n2 Open Access Computer File Diskette (Open Shelves)
Searching...

On Order

Summary

Summary

Combining neural networks and fuzzy systems, this presents neural networks as trainable dynamical systems and develops mechanisms and principles of adaption, self-organization, covergence and global stability. It also includes the geometric theory of fuzzy sets, systems and associative memories.


Reviews 1

Choice Review

Kosko (University of Southern California) presents two important recent developments, neural networks and fuzzy systems, from a consistent systems dynamics point of view. Kosko, an active researcher in both fields, has written probably the first book that has discussed both these theories at once. He uses the mathematical tools of upper-division undergraduate curricula in engineering and science: calculus, including differential equations; linear algebra; and probability, to present the techniques, the basic theory, and some applications of neural networks and fuzzy systems, including many of the important stability and convergence theorems for neural networks, and presents a new, "geometric" interpretation of fuzzy sets. He also gives many insights into the interrelations of these two approaches, and includes a chapter relating fuzzy set theory to probability. The book comes with software to allow the reader to experiment with computer implementations of many of the neural networks and fuzzy systems presented. This book is much more mathematical and provides greater depth than books such as Philip D. Wasserman's Neural Computing: Theory and Practice (CH, Nov'89), which could serve as an excellent introduction to Kosko's book. Although difficult to follow in places, the authoritative coverage of two important new areas should make this book a valuable reference for upper-level undergraduates and faculty.-H. D. Warner, Western New England College