Does Diploidy A ect Evolutions of Hop eld Associative Memory ?

We apply genetic algorithms to the Hop eld's neural network model of associative memory. Previously, we observed that random synaptic weights of a network evolved to create the xed point attractors corresponding to a set of given patterns to be stored. In that simulation, a weight con guration was expressed as a sequence of genes which might be called a haploid chromosome. Then a population of these haploid chromosomes underwent evolution. In this paper, we employ diploid chromosomes, a pair of chromosomes. We have reported elsewhere two di erent versions of the evolution that uses diploid chromosomes. One is the evolution of the Hebbian synapses in which some of the synapses are adaptively pruned according to information in the diploid chromosomes. The other is the evolution of real-valued random synaptic weights which are encoded directly into diploid chromosomes. Here, we describe the evolution based on the latter scheme with the weights being restricted to take the value 1. keywords Hop eld model of associative memory, genetic algorithm, diploid chromosome.