Mean Boundedness, Global Attractivity and Almost Periodic Sequence of Stochastic Neural Networks with Discrete-Time Analogue

Abstract

A class of stochastic neural networks with discrete-time analogue is investigated in this paper. By employing contraction mapping principle and some stochastic analysis techniques, we establish some sufficient conditions for mean boundedness, global attractivity and almost periodic sequence of the model. An example and graphic illustrations are displayed to visually expound the main contributions. The research techniques in this literature are suitable for other stochastic models in science and engineering.