Robust exponential stability analysis for interval Cohen–Grossberg type BAM neural networks with mixed time delays

详细信息    查看全文

• 作者：Qingqing He (1)
  Deyou Liu (1)
  Huaiqin Wu (1)
  Sanbo Ding (1)
  
• 关键词：Neural networks ; Mixed time delays ; Robust exponential stability ; Homomorphic mapping ; Nonsmooth analysis approach
• 刊名：International Journal of Machine Learning and Cybernetics
• 出版年：2014
• 出版时间：February 2014
• 年：2014
• 卷：5
• 期：1
• 页码：23-38
• 全文大小：493 KB
• 作者单位：Qingqing He (1)
  Deyou Liu (1)
  Huaiqin Wu (1)
  Sanbo Ding (1)
  
  1. Department of Applied Mathematics, Yanshan University, Qinhuangdao, 066001, China
  
• ISSN：1868-808X

文摘

In this paper, the robust exponential stability issue for the interval Cohen–Grossberg type BAM neural networks with nonsmooth behaved functions and mixed time delays is investigated. Firstly, based on Homomorphic mapping theory and nonsmooth analysis approach, the existence and uniqueness of the equilibrium point are proved. Secondly, by applying linear matrix inequality (LMI), free-weighting matrix technique, and available Lyapunov-Krasovskii functional method, some delay-dependent conditions are achieved in terms of LMIs to ensure the considered neural network to be globally robustly exponentially stable. The results obtained in this paper are little conservative compared with the previous results in the literature. Finally, two simulation examples are given to illustrate the validity of the theoretical results.