Lmi-Based asymptotic Stability Analysis of Neural Networks with Time-Varying Delays
Lmi-Based asymptotic Stability Analysis of Neural Networks with Time-Varying Delays
复制标题
DOI：
10.1142/s0129065708001567
复制
发表时间：
2008-06
影响因子：
8
通讯作者：
Tao Li;Changyin Sun;Xianlin Zhao;Chong Lin
中科院分区：
文献类型：
--
作者：
Tao Li;Changyin Sun;Xianlin Zhao;Chong Lin
研究了一类具有时变时滞的神经网络的全局渐近稳定性问题，其中激励函数既不是单调的，也不是可微的，更不是有界的.通过构造适当的李雅普诺夫泛函，结合线性矩阵不等式（LMI）技术，得到了关于不同类型时变时滞的新的全局渐近稳定性判据.结果表明，该准则比现有的一些准则具有更小的保守性。数值例子证明了所提出的方法的适用性。
The problem of the global asymptotic stability for a class of neural networks with time-varying delays is investigated in this paper, where the activation functions are assumed to be neither monotonic, nor differentiable, nor bounded. By constructing suitable Lyapunov functionals and combining with linear matrix inequality (LMI) technique, new global asymptotic stability criteria about different types of time-varying delays are obtained. It is shown that the criteria can provide less conservative result than some existing ones. Numerical examples are given to demonstrate the applicability of the proposed approach.