脉冲耦合复值神经网络的全局渐近同步  

On Global Asymptotic Synchronization of Impulsively Coupled Neural Networks with Complex Values

作　　者：冯靓 胡成[1] 于娟[1] FENG Liang;HU Cheng;YU Juan(School of Mathematics and System Science,Xinjiang University,Urumqi 830046,China)

机构地区：[1]新疆大学数学与系统科学学院,乌鲁木齐830046

出　　处：《西南师范大学学报（自然科学版）》2022年第3期9-15,共7页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：新疆自然科学基金项目(2021D01D10);国家自然科学基金项目(61963033)。

摘　　要：本文研究多个复值神经网络在脉冲耦合机制下形成复杂网络系统的全局渐近同步问题.首先,基于序列连通和Dirac函数,引入网络节点仅在离散时刻进行信息交互的脉冲耦合策略.其次,通过直接误差方法及迭代思想建立脉冲耦合复值神经网络渐近同步的判别条件.最后,给出相关数值实例及仿真来验证理论结果的正确性和有效性.In this paper,the global asymptotic synchronization has been studied for a class of complex networks formed by complex-valued neural networks based on impulsive coupling.Firstly,by virtue of the idea of sequential connectivity,an impulsive coupling strategy is introduced,in which the network nodes exchange information only at some discrete times.Secondly,in the direct error method and with the iterative idea,the sufficient conditions of asymptotical synchronization are established for the coupled complex-valued neural networks under this switching coupling strategy.Finally,a numerical example with simulation is provided to verify the correctness and validity of the theoretical results.

关 键 词：复值神经网络 脉冲耦合 渐近同步 序列连通性 直接误差方法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]