Application of an Evolution Strategy to the Hop eld Model of Associative Memory

| We apply evolutionary computations to Hopeld's neural network model of associative memory. In the Hop eld model, almost in nite number of combinations of synaptic weights give a network a function of associative memory. Furthermore, there is a trade-o between the storage capacity and size of basin of attraction. Therefore, the model can be thought of as a test suite of multi-modal and/or multi-objective function optimization. As preliminary stages, we investigate the basic behaviors of associative memory under simple evolutionary processes. In this paper, we present some experiments using an evolution strategy.