Performance enhancement of Willshaw type networks through the use of limit cycles

Abstract

Simulation results of a Willshaw type model for storing sparsely coded patterns are presented. It is suggested that random patterns can be stored in Willshaw type models by transforming them into a set of sparsely coded patterns and retrieving this set as a limit cycle. In this way, the number of steps needed to recall a pattern will be a function of the amount of information the pattern contains. A general algorithm for simulating neural networks with sparsely coded patterns is also discussed, and, on a fully connected network of N=36864 neurons (1.4×10 9 couplings), it is shown to achieve effective updaping speeds as high as 1.6×10 11 coupling evaluations per second on one Cray-YMP processor