Neural Processing Letters ( IF 3.1 ) Pub Date : 2021-02-04 , DOI: 10.1007/s11063-020-10342-4 Shuai Zhang , Yongqing Yang , Li Li , Dinghui Wu
In this paper, quasi-synchronization of fractional-order complex-valued memristive recurrent neural networks with switching jumps mismatch is investigated. Complex-valued systems are divided into two real-valued systems, which can avoid discussing the strict constraints in complex-value domain. A lemma is derived to deal with the mismatch. Under the framework of Fillipov’s solution, the sufficient conditions of quasi-synchronization are obtained by constructing suitable Lyapunov function. Besides, the error levels of quasi-synchronization are obtained. Some comparisons with existing results are given to verify the improvements. Two numerical simulations are given to demonstrate the effectiveness of the derived conditions.
中文翻译:
具有切换跳跃不匹配的分数阶复数值忆阻递归神经网络的拟同步
本文研究了具有切换跳变不匹配的分数阶复数值忆阻递归神经网络的准同步。复杂值系统分为两个实值系统,可以避免讨论复杂值域中的严格约束。引理可以解决不匹配问题。在菲利波夫解决方案的框架下,通过构造合适的李雅普诺夫函数获得了充分的准同步条件。此外,获得了准同步的误差等级。与现有结果进行了一些比较,以验证改进。给出了两个数值模拟,以证明导出条件的有效性。