Implementation of Hopfield associative memory with evolutionary algorithm and MC-adaptation rule for pattern storage

Abstract

This paper describes the strategy for implementation of Hopfield neural network as associative memory with the genetic algorithm and the Monte Carlo-(MC-) adaptation rule for pattern storage. In the Hopfield type neural networks of associative memory, the appropriate arrangement of synaptic weights provides an associative memory feature in the network. The fixed-point stable state of this model represents the appropriate storage of the input patterns. The aim is to obtain the optimal weight matrix for efficient recalling of any prototype input pattern. The performance of the Hopfield neural network, especially the capacity and the quality of the recalling, can be greatly improved by making use of genetic algorithm and MC-adaptation rule. The experiments consider a neural network trained with multiple numbers of patterns using the Hebbian learning rule. In most cases, the recalling of patterns using genetic algorithm with MC-adaptation rule seems to give better results than the conventional hebbian rule, MC-adaptation rule and simple genetic algorithm recalling techniques. © 2012 Springer India Pvt. Ltd.