Global exponential dissipativity and stabilization of memristor-based recurrent neural networks with time-varying delays
Global exponential dissipativity and stabilization of memristor-based recurrent neural networks with time-varying delays
复制标题
DOI：
10.1016/j.neunet.2013.08.002
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Zhenyuan Guo;Jun Wang;Zheng Yan
中科院分区：
文献类型：
--
作者：
Zhenyuan Guo;Jun Wang;Zheng Yan
研究了具有时变时滞的基于忆阻器的递归神经网络的全局指数耗散性。通过构造适当的Lyapunov泛函，利用M-矩阵理论和LaSalle不变原理，对全局指数耗散集进行了参数刻画。本文证明了n元记忆阻器神经网络存在2个2n2−n平衡点，且它们位于导出的全局吸引集中。研究还表明，基于忆阻器的时变时滞递归神经网络，通过使用具有适当增益的线性状态反馈控制律，在状态空间的原点是可镇定的。最后，对两个数值算例进行了详细的讨论，以说明结果的特点。
This paper addresses the global exponential dissipativity of memristor-based recurrent neural networks with time-varying delays. By constructing proper Lyapunov functionals and using M-matrix theory and LaSalle invariant principle, the sets of global exponentially dissipativity are characterized parametrically. It is proven herein that there are 2 2 n 2− n equilibria for an n-neuron memristor-based neural network and they are located in the derived globally attractive sets. It is also shown that memristor-based recurrent neural networks with time-varying delays are stabilizable at the origin of the state space by using a linear state feedback control law with appropriate gains. Finally, two numerical examples are discussed in detail to illustrate the characteristics of the results.