Robust stability of stochastic delayed additive neural networks with Markovian switching
Robust stability of stochastic delayed additive neural networks with Markovian switching
复制标题
DOI：
10.1016/j.neunet.2007.07.003
复制
发表时间：
2007-09
期刊：
影响因子：
--
通讯作者：
He Huang;D. Ho;Yuzhong Qu
中科院分区：
文献类型：
--
作者：
He Huang;D. Ho;Yuzhong Qu
研究了具有马尔可夫切换的随机区间时滞可加神经网络的鲁棒稳定性问题。时间延迟被假定为是时变的。在这样的神经网络中，随机系统，区间系统，时变时滞系统和马尔可夫切换的特点被考虑。首次提出了这类神经网络的数学模型。其次，研究了马尔可夫切换SIDANN的均方全局指数稳定性。基于李雅普诺夫方法，给出了几个稳定性条件，这些条件可以用线性矩阵不等式表示。作为进一步的结果，本文还讨论了具有时变时滞的随机区间可加性神经网络。给出了判定其稳定性的一个充分条件。最后，两个仿真例子来说明所开发的结果的有效性。
This paper is concerned with the problem of robust stability for stochastic interval delayed additive neural networks (SIDANN) with Markovian switching. The time delay is assumed to be time-varying. In such neural networks, the features of stochastic systems, interval systems, time-varying delay systems and Markovian switching are taken into account. The mathematical model of this kind of neural networks is first proposed. Secondly, the global exponential stability in the mean square is studied for the SIDANN with Markovian switching. Based on the Lyapunov method, several stability conditions are presented, which can be expressed in terms of linear matrix inequalities. As a subsequent result, the stochastic interval additive neural networks with time-varying delay are also discussed. A sufficient condition is given to determine its stability. Finally, two simulation examples are provided to illustrate the effectiveness of the results developed.