Novel delay-dependent robust stability criteria for neutral stochastic delayed neural networks

This paper is concerned with the globally exponential stability in mean square and almost surely exponential stability for neutral stochastic delayed neural networks. By constructing an appropriate Lyapunov–Krasovskii functional and with the help of the semimartingale convergence theorem, some delay-dependent sufficient conditions to guarantee the globally exponential stability in mean square and almost surely exponential stability of such systems are obtained in terms of the linear matrix inequality (LMI), which can be regarded as some less conservative criteria than some existing results when stochastic delayed neural networks of neutral type are designed. Finally, two illustrative numerical examples are given to demonstrate the advantages and applicabilities of the proposed results.