Share Email Print

Proceedings Paper

Enhanced Memory Capacity Of A Hopfield Neural Network
Author(s): M. J. Little; C. S. Bak
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

The performance of an associative memory based on the Hopfield Model of a neural network is data dependent. When programmed memories are too similar (a small Hamming distance between memories) the associative memory system is easily confused; settling either to incorrect or in some cases, undefined states. This paper describes a series of computer simulations performed on a 100-node Hopfield network. The programs were written in the APL language, which is highly efficient for this type of system. The simulations examined the sources of confusion and led to a preprocessing approach which substantially reduces the confusion. The simulations were also extended in the direction of coupling several small neural networks to form one integrated low-confusion associative memory. The coupling of the neural subnetworks was through a voting scheme wherein each node of a subnetwork consulted the analogous node of the other subnetworks; the decision to change state or remain the same is based on majority rule. The performance of these two associative memory systems is detailed and compared to a conventional Hopfield system.

Paper Details

Date Published: 23 March 1986
PDF: 7 pages
Proc. SPIE 0698, Real-Time Signal Processing IX, (23 March 1986); doi: 10.1117/12.976257
Show Author Affiliations
M. J. Little, Hughes Research Laboratories (United States)
C. S. Bak, Hughes Research Laboratories (United States)

Published in SPIE Proceedings Vol. 0698:
Real-Time Signal Processing IX
William J. Miceli, Editor(s)

© SPIE. Terms of Use
Back to Top