Share Email Print

Proceedings Paper

Chaotic neurochips for fuzzy computing
Author(s): Harold H. Szu; Lotfi A. Zadeh; Charles C. Hsu; Joseph T. DeWitte; Gyu Moon; Desa Gobovic; Mona E. Zaghloul
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A massive chaotic neural network (CNN) is demonstrated with a fixed-point Hebbian synaptic weight dynamic: an instantaneous input, and a piecewise negative logic output. The variable slope of the output versus the input becomes a software control of the collective chaos hardware. Two applications are given. The mean synaptic weight field plays an important role for fast pattern recognition capability in examples of both the habituation and the novelty detections. Another novel usage of CNN is to be a bridge between neural learning and learnable fuzzy logic.

Paper Details

Date Published: 1 March 1994
PDF: 16 pages
Proc. SPIE 2037, Chaos/Nonlinear Dynamics: Methods and Commercialization, (1 March 1994); doi: 10.1117/12.167517
Show Author Affiliations
Harold H. Szu, Naval Surface Warfare Ctr. (United States)
Lotfi A. Zadeh, Univ. of California/Berkeley (United States)
Charles C. Hsu, George Washington Univ. (United States)
Joseph T. DeWitte, George Washington Univ. (United States)
Gyu Moon, Hallym Univ. (South Korea)
Desa Gobovic, George Washington Univ. (United States)
Mona E. Zaghloul, George Washington Univ. (United States)

Published in SPIE Proceedings Vol. 2037:
Chaos/Nonlinear Dynamics: Methods and Commercialization
Helena S. Wisniewski, Editor(s)

© SPIE. Terms of Use
Back to Top