Multistability Analysis of Quaternion-Valued Neural Networks With Time Delays
Multistability Analysis of Quaternion-Valued Neural Networks With Time Delays
复制标题
DOI：
10.1109/tnnls.2018.2801297
复制
发表时间：
2018-03
影响因子：
10.4
通讯作者：
Q. Song;Xiaofeng Chen
中科院分区：
文献类型：
--
作者：
Q. Song;Xiaofeng Chen
本文介绍了随时间延迟的四元基因值神经网络（QVNN）的多稳定性问题。通过使用不平等技术，提出了足够的条件，以实现延迟QVNN的界限和全球吸引力。基于激活函数的几何特性，获得了几个标准，以确保存在$ 81^{n} $平衡点，$ 16^{n} $的本地稳定。提供了两个数值示例，以说明获得结果的有效性。
This paper addresses the multistability issue for quaternion-valued neural networks (QVNNs) with time delays. By using the inequality technique, sufficient conditions are proposed for the boundedness and the global attractivity of delayed QVNNs. Based on the geometrical properties of the activation functions, several criteria are obtained to ensure the existence of $81^{n}$ equilibrium points, $16^{n}$ of which are locally stable. Two numerical examples are provided to illustrate the effectiveness of the obtained results.