Context-Dependent Processing of Spatiotemporal Patterns Based on Interaction Between Neurodynamical Systems

Abstract

Dynamics of traditional neural network models are generally time-invari-ant. For that reason, they have limitations in context-dependent processing. We present a new method, dynamic desensitization, of varying neurodynamics continuously and construct a basic model of interaction between neurodynamical systems. This model comprises two nonmonotone neural networks storing sequential patterns as trajectory attractors. The dynamics of respective networks are modified according to the states of other networks. Using numerical experiments, we also show that the model can recognize and recall complex sequences with identical patterns in different positions.