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

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