Skip to main content
Log in

Delay-independent stability of stochastic reaction–diffusion neural networks with Dirichlet boundary conditions

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

Abstract

This paper deals with the problem of global stability of stochastic reaction–diffusion recurrent neural networks with continuously distributed delays and Dirichlet boundary conditions. The influence of diffusion, noise and continuously distributed delays upon the stability of the concerned system is discussed. New stability conditions are presented by using of Lyapunov method, inequality techniques and stochastic analysis. Under these sufficient conditions, globally exponential stability in the mean square holds, regardless of system delays. The proposed results extend those in the earlier literature and are easier to verify.

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

Access this article

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

  1. Grossberg S (1988) Nonlinear neural networks: principles, mechanisms and architectures. Neural Netw 1:17–61

    Article  Google Scholar 

  2. Liao X, Waong K, Leung SC, Wu Z (2001) Hopfield bifurcation and chaos in a single delayed neuron equation with non-monotonic activation function. Chaos Solitons Fractals 12:1535–1547

    Article  MATH  MathSciNet  Google Scholar 

  3. Arik S (2002) An analysis of global asymptotic stability of delayed cellular neural networks. IEEE Trans Neural Netw 13:1239–1242

    Article  Google Scholar 

  4. Cao J (2001) Global stability conditions for delayed CNNs. Circuits Syst I 48:1330–1333

    Article  MATH  Google Scholar 

  5. Chen T, Amari S (2001) Stability of asymmetric Hopfield networks. IEEE Trans Neural Netw 12:159–163

    Article  Google Scholar 

  6. Chen W, Guan Z, Lu X (2004) Delay-dependent exponential stability of neural networks with variable delays. Phys Lett A 326:355–363

    Article  MATH  MathSciNet  Google Scholar 

  7. Cohen MA, Grossberg S (1983) Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans Syst Man Cybern 13:815–826

    MATH  MathSciNet  Google Scholar 

  8. Song Q, Cao J, Zhao Z (2006) Periodic solutions and its exponential stability of reaction–diffusion recurrent neural networks with continuously distributed delays. Nonlinear Anal Real World Appl 7:65–80

    Article  MATH  MathSciNet  Google Scholar 

  9. Haykin S (1994) Neural networks. Prentice-Hall, Englewood Cliffs

    MATH  Google Scholar 

  10. Song Q, Cao J (2005) Global exponential stability and existence of periodic solutions in BAM networks with delays and reactionCdiffusion terms. Chaos Solitons Fractals 23:421–430

    Article  MATH  MathSciNet  Google Scholar 

  11. Zhao Y, Wang G (2005) Existence of periodic oscillatory solution of reaction–diffusion neural networks with delays. Phys Lett A 343:372–383

    Article  MATH  MathSciNet  Google Scholar 

  12. Liang J, Cao J (2003) Global exponential stability of reaction–diffusion recurrent neural networks with time-varying delays. Phys Lett A 314:434–442

    Article  MATH  MathSciNet  Google Scholar 

  13. Wang L, Gao Y (2006) Global exponential robust stability of reactionCdiffusion interval neural networks with time-varying delays. Phys Lett A 350:342–348

    Article  MathSciNet  Google Scholar 

  14. Wang L, Xu D (2003) Asymptotic behavior of a class of reactionCdiffusion equations with delays. Math Anal Appl 281:439–453

    Article  MATH  MathSciNet  Google Scholar 

  15. Zhao Z, Song Q, Zhang J (2006) Exponential periodicity and stability of neural networks with reaction–diffusion terms and both variable and unbounded delays. Comput Math Appl 51:475–486

    Article  MATH  MathSciNet  Google Scholar 

  16. Lu J (2008) Global exponential stability and periodicity of reaction–diffusion delayed recurrent neural networks with Dirichlet boundary conditions. Chaos, Solitons Fractals 35:116–125

    Article  MATH  MathSciNet  Google Scholar 

  17. Arnold L (1972) Stochastic differential equations: theory and applications. Wiley, New York

    Google Scholar 

  18. Hu J, Zhong S, Liang L (2006) Exponential stability of stochastic delayed cellular neural networks. Chaos, Solitions Fractals 27:1006–1010

    Article  MATH  MathSciNet  Google Scholar 

  19. Mao X (1997) Stochastic differential equations and applications. Ellis Horwood, Chichester

  20. Karatzas I, Shreve SE (1991) Brownian motion and stochastic calculus, 2nd edn. Springer, Berlin

  21. Lu J, Lu L (2007) Global exponential stability and periodicity of reaction–diffusion recurrent neural networks with distributed delays and Dirichlet boundary conditions. Chaos, solitons Fractals. doi:10.1016/j.chaos.2007.06.040

  22. Yang H, Chu T (2007) LMI conditions for the stability of neural networks with distributed delays. Chaos Solitons Fractals 34:557–563

    Article  MATH  MathSciNet  Google Scholar 

  23. Song Q, Cao J (2006) Stability analysis of Cohen-Grossberg neural networks with both time-varying and continuously distributed delays. Comput Appl Math 197:188–203

    Article  MATH  MathSciNet  Google Scholar 

  24. Zhang J (2003) Global exponential stability of neural networks with variable delays. IEEE Trans Circuits Syst I 50:288–290

    Article  Google Scholar 

Download references

Acknowledgements

The authors are grateful to the referees for their careful reading and very constructive comments on the original manuscript.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jun Peng.

Additional information

Research supported by National Science Foundation of China (No. 10371133).

Rights and permissions

Reprints and permissions

About this article

Cite this article

Liu, Z., Peng, J. Delay-independent stability of stochastic reaction–diffusion neural networks with Dirichlet boundary conditions. Neural Comput & Applic 19, 151–158 (2010). https://doi.org/10.1007/s00521-009-0268-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-009-0268-9

Keywords

Navigation