A neural network model of hysteresis

Abstract

Hysteresis is an effect of memory, which is frequently observed in the realm of nature. The purpose of this paper is trying to understand more of it, such that we may achieve better performance from the systems which are hysteresis-embedded. A hypothesis-based neural network model is offered in this paper. We name it the Synchronous Delay Network (SDN) model. It can be realized as a feed-forward neural network. We also discuss the possible applications in this paper.