Journal
NEUROCOMPUTING
Volume 151, Issue -, Pages 790-797Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2014.10.020
Keywords
Discrete-time recurrent neural networks; Mixed time-delays; Mean-square exponential stability; Stochastic system; Linear matrix inequalities (LMIs)
Categories
Funding
- National Natural Science Foundation of China [61403113]
- Zhejiang Provincial Natural Science Foundation of China [LQ14F030010]
- Scientific Research Foundation of Hangzhou Dianzi University [KYS065613036]
Ask authors/readers for more resources
In this paper, the mean-square exponential stability problem for discrete-time recurrent neural networks with time-varying discrete and distributed delays is investigated. Considering the delay distributions, a novel class of Lyapunov functional is introduced. By exploiting all possible information in mixed time delays, a sufficient condition for the whole system to be mean-square exponentially stable is given. Numerical examples are proposed to illustrate the effectiveness of the method, and show that by using the approach in this paper, the obtained results are less conservative than the existing ones. (C) 2014 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available