Robust stability of uncertain Markovian jump discrete-time recurrent neural networks with time delays

This article is concerned with robust stochastic stability for a class of uncertain Markovian jump discrete-time recurrent neural networks (MJDRNNs) with time delays. The uncertainty is assumed to be of the norm-bounded form. By employing the Lyapunov functional and linear matrix inequality (LMI) approach, some sufficient criteria are proposed for the robust stochastic stability in the mean square of the MJDRNNs with constant or mode-dependent time delays. The proposed LMI-based results are computationally efficient as they can be solved numerically using standard commercial software. The validity of the obtained results are further illustrated by two simulation examples.