Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

On the robustness of global exponential stability for hybrid neural networks with noise and delay perturbations

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The paper is concerned with the robustness of global exponential stability of hybrid neural networks subject to noise and delay simultaneously. Given a globally exponentially stable hybrid neural network, the aim of the paper is to characterize how much delay and noise intensity hybrid neural networks can bear such that the perturbed hybrid neural network remains globally exponentially stable, in the presence of delay and noise simultaneously. Numerical examples are provided to illustrate the result.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Carpenter G (1989) Neural network models for pattern recognition and associative memory. Neural Netw 2:243–257

    Article  Google Scholar 

  2. Zeng Z, Huang D, Wang Z (2005) Memory pattern analysis of cellular neural networks. Phys Lett A 342:114–128

    Article  MATH  Google Scholar 

  3. Park JH, Kwon OM, Lee SM (2008) A new stability criterion for bidirectional associative memory neural networks of neutral-type. Appl Math Comput 199(2):716–722

    Article  MathSciNet  MATH  Google Scholar 

  4. Cao J, Yuan K, Li H (2006) Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays. IEEE Trans Neural Netw 17(6):1646–1651

    Article  Google Scholar 

  5. Xu S, Lam J, Ho DWC (2006) A new LMI condition for delay dependent asymptotic stability of delayed Hopfield neural networks. IEEE Trans Circuits Syst II Exp Briefs 53(3):230–234

    Article  Google Scholar 

  6. Wu A, Zhang J, Zeng Z (2011) Dynamic behaviors of a class of memristor-based Hopfield networks. Phys Lett A 375:1661–1665

    Article  MathSciNet  MATH  Google Scholar 

  7. Zhang G, Shen Y, Sun J (2012) Global exponential stability of a class of memristor-based recurrent neural networks with time-varying delays. Neurocomputing 97(15):149–154

    Article  Google Scholar 

  8. Shen Y, Wang J (2012) Robustness analysis of global exponential stability of recurrent neural networks in the presence of time delays and random disturbances. IEEE Trans Neural Netw 23(1):87–96

    Article  Google Scholar 

  9. Wu A, Wen S, Zeng Z (2012) Synchronization control of a class of memristor-based recurrent neural networks. Inf Sci 183:106–116

    Article  MathSciNet  MATH  Google Scholar 

  10. Forti M, Tesi A (1995) New conditions for global stability of neural networks with application to linear and quadratic programming problems. IEEE Trans Circuits Syst I Fundam Theory Appl 42(7):354–366

    Article  MathSciNet  MATH  Google Scholar 

  11. Mao X (2006) Stochastic differential equations with Markovian Switching. Imperial College Press, London

    Book  MATH  Google Scholar 

  12. Sun Y, Cao J (2008) Stabilization of stochastic delayed neural networks with Markovian switching. Asian J Control 10(3):327–340

    Article  MathSciNet  Google Scholar 

  13. Hu G, Liu M, Mao X, Song M (2009) Noise suppresses exponential growth under regime switching. J Math Anal Appl 355:783–795

    Article  MathSciNet  MATH  Google Scholar 

  14. Deng F, Luo Q, Mao X (2012) Stochastic stabilization of hybrid differential equations. Automatica doi:10.1016/j.automatica.2012.06.044.

  15. Shen Y, Wang J (2007) Noise-induced stabilization of the recurrent neural networks with mixed time varying delays and Markovian-switching parameters. IEEE Trans Neural Netw 18(6):1857–1862

    Article  Google Scholar 

  16. Zhu S,Shen Y, Chen G (2010) Noise suppress or express exponential growth for hybrid Hopfield neural networks. Phys Lett A 374(19–20):2035–2043

    Article  MathSciNet  MATH  Google Scholar 

  17. Zhu S, Shen Y (2012) Robustness analysis of global exponential stability of neural networks with Markovian switching in the presence of time varying delays or noises. Neural Comput Appl doi:10.1007/s00521-012-1105-0

  18. Wang Z, Liu Y, Liu X (2006) Exponential stability of delayed recurrent neural networks with Markovian jumping parameters. Phys Lett A 356:346–352

    Article  MATH  Google Scholar 

  19. Shen Y, Wang J (2009) Almost sure exponential stability of recurrent neural networks with Markovian switching. IEEE Trans Neural Netw 20(5):840–855

    Article  Google Scholar 

  20. Wang G, Cao J, Liang J (2009) Exponential stability in the means quare for stochastic neural networks with mixed time-delays and Markovian jumping parameters. Nonlinear Dyn 57(1-2):209–218

    Article  MathSciNet  MATH  Google Scholar 

  21. Huang H, Ho DWC, Qu Y (2007) Robust stability of stochastic delayed additive neural networks with Markovian switching. Neural Netw 20:799–809

    Article  MATH  Google Scholar 

  22. Huang H, Qu Y, Li H (2005) Robust stability analysis of switched Hopfield neural networks with time-varying delay under uncertainty. Phys Lett A 345:345–354

    Article  MATH  Google Scholar 

  23. Wan L, Zhou Q (2007) Convergence analysis of stochastic hybrid bidirectional associative memory neural networks with delays. Phys Lett A 370(5-6):423–432

    Article  Google Scholar 

  24. Liao XF, Wong K (2003) Global exponential stability of hybrid bidirectional associative memory neural networks with discrete delays. Phys Rev E 67:0402901

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgments

The authors would like to thank Prof. John MacIntyre and anonymous referees for their constructive suggestions and comments. The work is supported by the Research Fund for Wuhan Polytechnic University under Grant 2012Y16, the Fundamental Research Funds for the Central Universities, the China Postdoctoral Science Foundation under Grant 2012M511615, and the State Key Program of National Natural Science of China under Grant 61134012.

Author information

Authors and Affiliations

  1. School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, 430073, China

    Feng Jiang

  2. School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, 430023, China

    Hua Yang

  3. The Key Laboratory of Ministry of Eduction for Image Processing and Intelligent Control, Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China

    Yi Shen

Authors
  1. Feng Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hua Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Feng Jiang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Jiang, F., Yang, H. & Shen, Y. On the robustness of global exponential stability for hybrid neural networks with noise and delay perturbations. Neural Comput & Applic 24, 1497–1504 (2014). https://doi.org/10.1007/s00521-013-1374-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-013-1374-2

Keywords

Search

Navigation