当前位置: X-MOL 学术Chaos Solitons Fractals › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Global quasi-synchronization of complex-valued recurrent neural networks with time-varying delay and interaction terms
Chaos, Solitons & Fractals ( IF 7.8 ) Pub Date : 2021-09-06 , DOI: 10.1016/j.chaos.2021.111323
Ankit Kumar 1 , Subir Das 1 , Vijay K. Yadav 1 , Rajeev 1
Affiliation  

In this article, the global quasi-synchronization of complex-valued recurrent neural networks (CVRNNs) with time-varying delays and interaction terms has been investigated. It is based on the standard Lyapunov stability theory and matrix measure method employed with the nonlinear Lipschitz activation functions. A sufficient condition for global quasi-synchronization of the complex-valued recurrent neural network model is shown in an effective way through a proper description of Lyapunov-stability technique. This article provides quite a new result for the CVRNNs having time-varying delays and interaction terms. Finally, a numerical example is considered to show the viability and unwavering quality of our theoretical results under several conditions.



中文翻译:

具有时变延迟和交互项的复值递归神经网络的全局准同步

在本文中,研究了具有时变延迟和交互项的复值递归神经网络 (CVRNN) 的全局准同步。它基于标准的 Lyapunov 稳定性理论和矩阵测度方法,采用非线性 Lipschitz 激活函数。通过对李雅普诺夫稳定性技术的适当描述,给出了复值递归神经网络模型全局准同步的充分条件。本文为具有时变延迟和交互项的 CVRNN 提供了一个相当新的结果。最后,一个数值例子被认为是在几种条件下我们的理论结果的可行性和坚定不移的质量。

更新日期:2021-09-06
down
wechat
bug