Nonsmooth Finite-Time Synchronization of Switched Coupled Neural Networks
Nonsmooth Finite-Time Synchronization of Switched Coupled Neural Networks
复制标题
开关耦合神经网络的非光滑有限时间同步
DOI：
10.1109/tcyb.2015.2477366
复制
发表时间：
2016-10-01
影响因子：
11.8
通讯作者：
Song, Qiang
中科院分区：
文献类型：
--
作者：
Liu, Xiaoyang;Cao, Jinde;Song, Qiang
研究了具有不连续或连续激活的开关耦合神经网络的有限时间同步问题。基于非光滑分析的框架，设计了一些不连续或连续的控制器来强制耦合网络同步到一个孤立的神经网络。利用众所周知的非线性系统有限时间稳定性定理，导出了保证时域变换的几个充分条件。与以往的文献相比，在激活和控制器都不连续的情况下，才能实现这样的同步目标。本文所得到的结果包括并推广了前人关于具有Lipschitz连续条件的耦合网络同步问题的研究成果。此外，还估计了同步稳定时间的上界。最后通过数值仿真验证了理论结果的有效性。
This paper is concerned with the finite-time synchronization (FTS) issue of switched coupled neural networks with discontinuous or continuous activations. Based on the framework of nonsmooth analysis, some discontinuous or continuous controllers are designed to force the coupled networks to synchronize to an isolated neural network. Some sufficient conditions are derived to ensure the FTS by utilizing the well-known finite-time stability theorem for nonlinear systems. Compared with the previous literatures, such synchronization objective will be realized when the activations and the controllers are both discontinuous. The obtained results in this paper include and extend the earlier works on the synchronization issue of coupled networks with Lipschitz continuous conditions. Moreover, an upper bound of the settling time for synchronization is estimated. Finally, numerical simulations are given to demonstrate the effectiveness of the theoretical results.