Further Results on Input-to-State Stability of Stochastic Cohen–Grossberg BAM Neural Networks with Probabilistic Time-Varying Delays

摘要

In this article, the problem of stochastic Cohen–Grossberg Bidirectional Associative Memory (CGBAM) neural networks with probabilistic time-varying delay is analyzed by input-to-state stability theory. The stochastic variable with Bernoulli distribution gives the information of probabilistic time-varying delay and it is transformed into one with deterministic time-varying delay in the stochastic manner. Further, by constructing a novel Lyapunov–Krasovskii functional and utilizing Ito’s and Dynkin’s formula with stochastic analysis theory, the sufficient criterion is derived for the input-to-state stability of stochastic CGBAM neural networks. Finally, numerical examples are provided to examine the merits of the given method.