作　　者： ; ; ;

机构地区： 重庆教育学院计算机与现代教育技术系

出　　处： 《计算机应用研究》 2009年第4期1222-1224,1233,共4页

摘　　要： 采用It s微分公式和不等式分析技巧,研究了一类不确定随机离散分布时滞神经网络的鲁棒稳定性问题。该模型同时考虑了神经网络模型的两种扰动因素,即随机扰动与不确定性扰动。通过构造适当的Lyapunov泛函,以线性矩阵不等式形式给出了系统在均方根意义下的全局鲁棒稳定性判据,能够利用LM I工具箱很容易地进行检验。此外,仿真结果进一步证明了结论的有效性。 By Ito＇s differential formula and combining the method of inequality analysis, this paper investigated the problem of stochastic asymptotical stability of a class of uncertain stochastic neural networks with discrete and distributed delays. There were two kinds of disturbances which were unavoidable to be considered in neural networks. The parameter uncertainties are time-varying and norm-bounded. The time-delay factors are unknown and time-varying with known bounds. Based on Lya- punov-Krasovskii functional and stochastic analysis approaches, presented some new stability criteria in terms of linear matrix inequalities （LMIs） to guarantee the delayed neural network to be robustly stable in the mean square for all admissible uncer- tainties. It gave a numerical examples to demonstrate the usefulness of the proposed asymptotical stability criteria.

关 键 词： 鲁棒稳定性 随机神经网络 分布时滞 不确定性 线性矩阵不等式

领　　域： [自动化与计算机技术] [自动化与计算机技术]