Robust stability for uncertain stochastic neural network with delay and impulses

This paper devotes to the stochastic robust stability of uncertain neural networks with time-varying delay and impulses. By using Lyapunov function and stochastic analysis approaches, a sufficient condition is derived in terms of linear matrix inequality (LMI), which can guarantee the uncertain neural network to be robustly exponentially stable in the mean square for all admissible uncertainties. We also extend the delay fractioning approach to the uncertainty system by constructing a Lyapunov–Krasovskii functional and comparing to a linear discrete system. The estimation of decay rate of uncertain neural network can be obtained by estimation of the decay of the linear discrete system. Meanwhile, two examples with numerical simulations are given to illustrate the applicability of the results.