New robust stability of discrete-time stochastic neural networks with Markovian jumping parameters

The asymptotic stability in the mean square is studied for a class of discrete-time uncertain stochastic neural networks with Markovian jumping parameters in this paper. By introducing some free weighting matrices and constructing a right Lyapunov-Krasovskii functional, we get an novel global asymptotic stability criteria. Conditions are proposed to guarantee the robust stability of discrete-time uncertain stochastic neural networks via linear matrix inequality approach. Finally, a numerical example is given to illustrate the feasibility and effectiveness of the results.