具有混合时变时滞不连续激活函数神经网络的耗散和有限时间同步研究

GLOBAL DISSIPATIVITY AND FINITE-TIME SYNCHRONIZATION OF MIXED TIME-VARYING DELAYED NEURAL NETWORKS WITH DISCONTINUOUS ACTIVATIONS

本文研究了具有混合时变时滞不连续激活函数神经网络的耗散性和有限时间同步问题。首先,在推广Filippov微分包含理论的框架下,利用广义Halanay不等式和矩阵测度的方法,证明了神经网络Filippov解的全局耗散性。其次,利用不等式和一些分析技术,设计了时滞无关不连续反馈控制器,实现了神经网络驱动系统与响应系统的有限时间同步。最后,通过几个算例验证了理论结果的有效性和正确性。

In this paper,the dissipativity and finite-time synchronization of discontinuous activation function neural networks with mixed time-varying delays are studied.Firstly,under the framework of generalized Filippov differential inclusion theory,the global dissipativity of Filippov solution is proved by using generalized Halanay inequality and matrix measure.Secondly,by using inequalities and some analytical techniques,a delay-independent discontinuous feedback controller is designed to achieve finite-time synchronization between the neural network-driven system and the response system.Finally,several examples are given to verify the validity and correctness of the theoretical results.