DESIGN OF HOPFIELD-TYPE ASSOCIATIVE MEMORY WITH MAXIMAL BASIN OF ATTRACTION

Abstract

A method is described for enlarging as much as possible the basin of attraction of a Hopfield-type associative memory. The proposed learning rule, a minimum-overlap learning algorithm that includes a threshold parameter, enables a Hopfield-type associative memory to be designed so that the memory will have a maximal basin of attraction. A technique that diminishes the effect of the threshold on the minimum-overlap learning algorithm is devised. Simulation results show that the basin of attraction constructed by the proposed method is indeed larger than that constructed by several well known methods.