Title :
Large-capacity, noise-filtering, multi-level, associate memory system
Author_Institution :
Dept. of Electr. Eng., Southern Illinois Univ., Carbondale, IL
Abstract :
The dynamical properties of a neural circuit are studied by means of a modified Lyapunov theory. These properties include the criteria of stability, the domain of convergence, the initial-to-final mapping, and the programming of the connection matrix. All the theoretical predictions are verified numerically by computer experiments. Practical applications of this system are discussed
Keywords :
Lyapunov methods; content-addressable storage; filtering and prediction theory; neural nets; stability criteria; Lyapunov theory; associate memory system; connection matrix; convergence; dynamical properties; initial-to-final mapping; neural circuit; neural nets; noise-filtering; stability; Application software; Circuit noise; Circuit stability; Convergence; Stability criteria;
Conference_Titel :
System Theory, 1989. Proceedings., Twenty-First Southeastern Symposium on
Conference_Location :
Tallahassee, FL
Print_ISBN :
0-8186-1933-3
DOI :
10.1109/SSST.1989.72502
