Stability analysis of complex-valued neural networks with probabilistic time-varying delays
Stability analysis of complex-valued neural networks with probabilistic time-varying delays
复制标题
具有概率时变延迟的复值神经网络的稳定性分析
DOI：
10.1016/j.neucom.2015.02.015
复制
发表时间：
2015-07-02
期刊：
影响因子：
6
通讯作者：
Liu, Yurong
中科院分区：
文献类型：
--
作者：
Song, Qiankun;Zhao, Zhenjiang;Liu, Yurong
本文研究了具有概率时变时滞的复值神经网络的稳定性。建立了两个重要的积分不等式，其中包括詹森不等式的特例.通过构造适当的Lyapunov-Krasovskii泛函和利用不等式技巧，得到了保证该神经网络全局渐近稳定和指数稳定的时滞分布依赖的充分条件.这些条件用复值线性矩阵不等式表示，可以使用MATLAB中有效的YALMIP工具箱进行数值检查。最后给出了一个仿真实例，验证了所得结果的有效性. (C)2015 Elsevier B. V.版权所有。
In this paper, the stability of complex-valued neural networks with probabilistic time-varying delays is investigated. Two important integral inequalities that include Jensen's inequality as a special case are developed. By constructing proper Lyapunov-Krasovskii functional and employing inequality technique, several delay-distribution-dependent sufficient conditions are obtained to guarantee the global asymptotic and exponential stability of the addressed neural networks. These conditions are expressed in terms of complex-valued LMIs, which can be checked numerically using the effective YALMIP toolbox in MATLAB. An example with simulations is given to show the effectiveness of the obtained results. (C) 2015 Elsevier B.V. All rights reserved.