A model of dynamic associative memory

Abstract

A model of dynamic associative memories is proposed. The aim is to find all stored patterns, and to distinguish the stored and the spurious patterns. Aihara (1993) used chaotic neurons and showed that his model has a nonperiodic associative dynamics. In his model, however, it is difficult to distinguish the stored patterns from the others, because the state of the network changes continually. We propose such a new model of neurons that each neuron changes its output to the other when the accumulation of its internal state exceeds a certain threshold. By computer experiments, we show that the state of the network stays at the stored pattern for a while and then travels around to another pattern, and so on. Furthermore, when the number of the stored patterns is small, the stored and the spurious patterns can be distinguished using intervals of the network staying in these patterns.