Stability Analysis Of Stochastic Neural Networks With Time Delays

In this paper, some sufficient conditions about the stability of stochastic Recurrent neural networks and stochastic Cohen-Grossberg neural networks are obtained, by constructed a Lyapunov-Krasovskii functional, and applied the Ito formula, and used the linear matrix inequality and the Blythe-Liao-Mao inequality. The paper is divided into four chapters. Main contents are as follows:In the first chapter, the current status in neural networks and stochastic neural networks is briefly addressed, the development and applications of stochastic differential equation are introduced.In the second chapter, some definitions and notations are given in this chapter.In the third chapter, stability of stochastic Recurrent neural networks are stud-ied.Some sufficient conditions about the global asymptotic stability of stochastic Re-current neural networks with time-varying and neutral stochastic Recurrent neural net-works with time-varying delays are obtained, by constructed a Lyapunov-Krasovskii functional, and applied the Ito formula and used the linear matrix inequality.In the fourth chapter, stability of stochastic Cohen-Grossberg neural networks are studied. By constructing suitable Lyapunov-Krasovskii functional and employing the Blythe-Liao-Mao inequality and using the Ito formula we obtained some sufficient con-ditions ensuring the almost sure exponential stability of stochastic Cohen-Grossberg neural networks with time delays. By constructing suitable Lyapunov-Krasovskii func-tional and employing the linear matrix inequality inequality and using the Ito formula we obtained some sufficient conditions ensuring the mean square global asymptotic sta-bility of neutral stochastic Cohen-Grossberg neural networks with time-varying delays.