Stochastic stability analysis for neural networks with mixed time-varying delays

详细信息    查看全文

• 作者：Yuechao Ma ; Yuqing Zheng
• 关键词：Stochastic stability ; Markovian jumping ; Discrete time delays ; Distributed time delays ; Lyapunov–Krasovskii functional
• 刊名：Neural Computing & Applications
• 出版年：2015
• 出版时间：February 2015
• 年：2015
• 卷：26
• 期：2
• 页码：447-455
• 全文大小：271 KB
• 参考文献：1. Xu S, Lam J, Dwc Ho (2005) Novel global asymptotical stability criteria for delayed cellular neural networks. IEEE Trans Circuits Syst 52:349-53 CrossRef
  2. Chen A, Cao J, Huang L (2005) Global robust stability of interval cellular neural networks with time varying delays. Chaos Solitons Fractals 23(3):789-99 CrossRef
  3. Zhang Q, Wei X, Xu J (2006) Stability analysis for cellular neural networks with variable delays. Chaos Solitons Fractals 28(2):331-36 CrossRef
  4. Hong L, Bing C (2008) Robust exponential stability for delayed uncertain Hopfield neural networks with Markovian jumping parameters. Phys Lett A 372:4996-003 CrossRef
  5. Mao X (2002) Exponential stability of stochastic delay interval systems with Markovian switching. IEEE Trans Autom Control 47:1604-612 CrossRef
  6. Zhang J, Jin X (2000) Global stability analysis in delayed Hopfield neural network models. Neural Netw 13:745-53 CrossRef
  7. Cao J, Wang J (2003) Global asymptotic stability of reaction diffusion recurrent neural networks with time-varying delays. Phys Lett A 314:434-42 CrossRef
  8. Syed Ali M, Balasubramaniam P (2008) Robust stability for uncertain stochastic fuzzy BAM neural networks with time-varying delays. Phys Lett A 372(31):5159-166 CrossRef
  9. Balasubramaniam P, Lakshmanan S, Rakkiyappan R (2009) Delay-interval dependent robust stability criteria for stochastic neural networks with linear fractional uncertainties. Neurocomputing 72(16):3675-682 CrossRef
  10. Rakkiyappan R, Balasubramaniam P (2008) Delay-dependent asymptotic stability for stochastic delayed recurrent neural networks with time varying delays. Appl Math Comput 198(2):526-33 CrossRef
  11. Cao J, Wang J (2005) Global asymptotic and robust stability of recurrent neural networks with time delays. IEEE Trans Circuits Syst 23(1):221-29
  12. Zhang H, Liu Z, Wang Z (2010) Novel weighting delay-based stability criteria for recurrent neural networks with time-varying delays. IEEE Trans Neural Netw 21:91-06 CrossRef
  13. Huang C, Cao J (2009) Almost sure exponential stability of stochastic cellular neural networks with unbounded distributed delays. Neurocomputing 72(13-5):3352-356 CrossRef
  14. Rakkiyappan R, Balasubramaniam P (2008) LMI conditions for global asymptotic stability results for neutral-type neural networks with distributed time delays. Appl Math Comput 204(1):317-24 CrossRef
  15. Shi P, Zhang J, Qiu J, Xing L (2006) New global asymptotic stability criterion for neural networks with discrete and distributed delays. Proc Inst Mech Eng J Syst Control Eng 221:129-35
  16. Balasubramaniam P, Rakkiyappan R (2008) Global asymptotic stability of stochastic recurrent neural networks with multiple discrete delays and unbounded distributed delays. Appl Math Comput 204(2):680-86 CrossRef
  17. Cao J, Wang J (2003) Global asymptotic stability of a general class of recurrent neural networks with time-varying delays. IEEE Trans Circuits Syst 50(1):34-4 CrossRef
  18. Liu Y, Wang Z, Liu X (2008) On delay-dependent robust exponential stability of stochastic neural netw
• 刊物类别：Computer Science
• 刊物主题：Simulation and Modeling
  
• 出版者：Springer London
• ISSN：1433-3058

文摘

This paper is concerned with the problem of the stochastic stability analysis for Markovian jumping neural networks with time-varying delays and stochastic perturbation. Some criteria for the stability and robust stability of such neural networks are derived, by means of constructing suitable Lyapunov–Krasovskii functionals and a unified linear matrix inequality (LMI) approach. Note that the LMIs can be easily solved by using the Matlab LMI toolbox and no tuning of parameters is required. Finally, numerical examples are used to illustrate the effectiveness and advantage of the proposed techniques.