Stability Analysis For Stochastic Delay Neural Networks

In recent years, investigation in both theory and application of stochastic neural networks have received considerable attention, especially, stability of stochastic delay neural networks(global asymptotical stability and global exponential stability) are studied deeply, and have obtained a series of results. In this thesis, global asymptotical stability of stochastic distributed delay neural networks and global exponential stability of stochastic delay neural networks are studied, which based on the theory of stochastic differentical equation and the Lyapunov stability.Firstly, new theory for global asymptotical stability for stochastic distributed delay neural networks has been derived using an approach combining the Lyapunov-Krasovskii functional with differential inequality and LMI techniques, and we present numerical examples to illustrate the validity of the new theory, by LMI toolbox and Simulation of Matlab.Secondly, this paper considers global exponential stability of stochastic delay neural networks by constructing appropriate Lyapunov functionals, New criterions to satisfy global exponential stability of the system are gained. and a numerical Simulation is given to show the validity of new criterions.Finally, a summary of the paper is made, and the future research directions are forecasted.