Delay-dependent finite-time boundedness of a class of Markovian switching neural networks with time-varying delays

Qishui Zhong; Jun Cheng; Yuqing Zhao

doi:10.1016/j.isatra.2015.01.001

Delay-dependent finite-time boundedness of a class of Markovian switching neural networks with time-varying delays

ISA Trans. 2015 Jul:57:43-50. doi: 10.1016/j.isatra.2015.01.001. Epub 2015 Feb 13.

Authors

Qishui Zhong¹, Jun Cheng², Yuqing Zhao³

Affiliations

¹ School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, PR China. Electronic address: zhongqs@uestc.edu.cn.
² School of Electrical and Information Technology, Yunnan Minzu University, Kunming, Yunnan 650500, PR China. Electronic address: jcheng6819@126.com.
³ Faculty of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming, Yunnan 650201, PR China. Electronic address: kmyuqing@163.com.

PMID: 25683106
DOI: 10.1016/j.isatra.2015.01.001

Abstract

In this paper, a novel method is developed for delay-dependent finite-time boundedness of a class of Markovian switching neural networks with time-varying delays. New sufficient condition for stochastic boundness of Markovian jumping neural networks is presented and proved by an newly augmented stochastic Lyapunov-Krasovskii functional and novel activation function conditions, the state trajectory remains in a bounded region of the state space over a given finite-time interval. Finally, a numerical example is given to illustrate the efficiency and less conservative of the proposed method.

Keywords: Finite-time boundness; Markovian jump systems; Neural networks; Time delay.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Computer Simulation
Markov Chains
Models, Statistical*
Neural Networks, Computer*
Nonlinear Dynamics*
Stochastic Processes