Stability of Stochastic Bidirectional Associative Memory Neural Networks with Markovian Switching and Discrete Time Noises

This study focuses on the asymptotic stability (AS) and the exponential stability (ES) of stochastic bidirectional associative memory neural networks (SBAMNNs) with Markovian switching (MS) as well as discrete time noises (DTNs). The existing references regarding stability analysis of SBAMNNs mainly utilize the Lyapunov method as well as the linear matrix inequality to establish stability criteria. This paper uses the M-matrix property and a new Lyapunov functional dependent on the length of discrete observation interval to propose some stability theorems. Specifically, three sufficient criteria are provided for ensuring the mean-square AS and the mean-square ES of the global solution to SBAMNNs with MS and DTNs. In the end, a numerical example is provided to illustrate the feasibility of the presented theoretical findings.