人工神经网络
平衡点
类型(生物学)
指数稳定性
理论(学习稳定性)
数学
微分包含
点(几何)
应用数学
控制理论(社会学)
计算机科学
微分方程
数学分析
非线性系统
人工智能
控制(管理)
物理
几何学
机器学习
生物
量子力学
生态学
作者
Fanchao Kong,Quanxin Zhu
标识
DOI:10.1080/00207179.2020.1800100
摘要
In this paper, we aim to investigate the globally asymptotic stability of the equilibrium point for the discontinuous Cohen–Grossberg neural networks of neutral-type in Hale's form. The functional differential inclusions theory, inequality technique and the non-smooth Lyapunov–Krasovskii functional are invoked and some new delay independent sufficient conditions are derived. The considered neural system extends some previous related ones to the discontinuous case. In addition, the imposed essential condition ∑j=1ncij+<1 or ci+<1 (i=1,2,…n) in the previous researches on neutral-type neural networks in Hale's form will not be needed in this paper. Consequently, compared with the previous stability results on the neutral-type Cohen–Grossberg neural networks, the results established are more generalised and take more advantages. Finally, the effectiveness of the established results are validated via two numerical examples and simulations.
科研通智能强力驱动
Strongly Powered by AbleSci AI