一类随机递归神经网络的稳定性分析

Stability analysis for a class of stochastic recurrent neural networks

对一类具有时变时滞的随机递归神经网络模型,研究了其系统的全局渐近稳定性,并给出了一个新的控制器设计方法.基于逆最优方法和Lyapunov函数,在不需要求解Hamilton-Jacobi-Bellman方程情形下,对于一个有意义的成本函数,反馈控制器的设计既能使系统达到全局最优,又能保证系统的全局渐近稳定性.

The global asymptotic stability of a class of stochastic recurrent neural networks with time-varying delays is investigated in this paper,and a new controller design method is presented.The analysis tool developed in this paper is based on inverse optimal method and Lyapunov function,which do not require to solve Hamilton-Jacobi-Bellman equations.In addition,the design of the feedback controller can not only make the system achieve global optimization,but also ensure the global asymptotic stability of the system.