An asymptotical stability criterion for discrete-time stochastic neural networks with Markovian jumping and time-varying mixed delays
The global asymptotical stability problem is considered for a class of discrete-time stochastic recurrent neural networks(NNs) with Markovian jumping parameters and time-varying mixed delays in this paper. The mixed time delays include discrete delays and distributed delays, and both are assumed to be time-varying and belong to a given interval, which means that the lower and upper bounds of interval time-varying delays are available. The neural networks have a finite number of modes, and the modes may jump from one to another according to a discrete-time Markov chain. Based on the Lyapunov method and stochastic analysis approach, delay-interval dependent stability criterion is obtained in terms of linear matrix inequality(LMI) and generalizes existing results. Finally, a numerical example is given to demonstrate the effectiveness of the proposed results.
Discrete neural network Markovian jumping Time-delay Stability Linear matrix inequality (LMI)
Hongjun Chu Fang Wang Lixin Gao
Institute of Operations Research and Control Sciences, Wenzhou University, Zhejiang 325035, China
国际会议
The 22nd China Control and Decision Conference(2010年中国控制与决策会议)
徐州
英文
205-210
2010-05-26（万方平台首次上网日期，不代表论文的发表时间）