Skip to main content
SpringerLink
Log in

Delay-dependent exponential stability of recurrent neural networks with Markovian jumping parameters and proportional delays

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

Abstract

This paper deals with the global exponential stability problem of a class of recurrent neural networks with Markovian jumping parameters and proportional delays. Here the proportional delay is unbounded time-varying, which is different from unbounded distributed delay. The nonlinear transformation \(z(t)=x({\text {e}}^{t})\) transforms the recurrent neural networks with Markovian jumping parameters and proportional delays into the recurrent neural networks with Markovian jumping parameters, constant delays and variable coefficients. By constructing Lyapunov functional, a linear matrix inequality (LMI) approach is developed to establish a new delay-dependent global exponential stability sufficient condition in the mean square, which is related to the size of the proportional delay factor and can be easily checked by utilizing the numerically efficient MATLAB LMI toolbox, and no tuning of parameters is required. Two numerical examples and their simulations are given to illustrate the effectiveness of the obtained results.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Guo S, Huang L (2005) Periodic oscillation for a class of neural networks with variable coefficients. Nonlinear Anal RWA 6(3):545–561

    Article  MathSciNet  MATH  Google Scholar 

  2. Wang Z, Ho DWC, Liu X (2005) State estimation for delayed neural networks. IEEE Trans Signal Process 51(9):279–284

    Google Scholar 

  3. Liu Y, Wang Z, Liu X (2006) Global exponential stability of generalized recurrent neural networks with discrete and distributed delays. Neural Netw 19(5):667–675

    Article  MATH  Google Scholar 

  4. Song Q, Wang Z (2007) A delay-dependent LMI approach to dynamics analysis of discrete-time recurrent neural networks with time-varying delays. Phys Lett A 368(1–2):134–145

    Article  Google Scholar 

  5. Song Q (2008) Exponential stability of recurrent neural networks with both time-varying delays and general activation functions via LMI approach. Neurocomputing 71(13–15):2823–2830

    Article  Google Scholar 

  6. Kao Y, Gao C (2008) Global exponential stability analysis for cellular neural networks with variable coefficients and delays. Neural Comput Appl 17(3):291–296

    Article  MATH  Google Scholar 

  7. Chen W, Zheng W (2009) Global exponential stability of impulsive neural networks with variable delay: an LMI approach. IEEE Trans Circuits Syst I 56(6):1248–1259

    Article  MathSciNet  Google Scholar 

  8. Tan M (2010) Global asympotic stability of fuzzy cellular neural networks with unbounded distributed delays. Neural Process Lett 31(2):147–157

    Article  MathSciNet  Google Scholar 

  9. Li T, Song A, Fei S, Wang T (2010) Delay-derivative-dependent stability for delayed neural networks with unbound distributed delay. IEEE Trans Neural Netw 21(8):1365–1371

    Article  Google Scholar 

  10. Balasubramaniam P (2012) Synchronization of recurrent neural networks with mixed time-delays via output coupling with delayed feedback. Nonlinear Dyn 70(1):677–691

    Article  MathSciNet  MATH  Google Scholar 

  11. Rakkiyappan R, Balasubramaniam P (2010) On exponential stability results for fuzzy impulsive neural networks. Fuzzy Set Syst 161(13):1823–1835

    Article  MathSciNet  MATH  Google Scholar 

  12. Samidurai R, Sakthivel R, Anthoni SM (2009) Global asymptotic stability of BAM neural networks with mixed delays and impulses. Appl Math Comput 212:113–119

    MathSciNet  MATH  Google Scholar 

  13. Samidurai R (2010) Global exponential stability of neutral-type impulsive neural networks with discrete and distributed delays. Nonlinear Anal Hyb Syst 4(1):103–112

    Article  MathSciNet  MATH  Google Scholar 

  14. Fox L, Mayers DF (1971) On a functional differential equational. J Inst Math Appl 8(3):271–307

    Article  MathSciNet  MATH  Google Scholar 

  15. Derfel GA (1990) Kato problem for functional equational and difference schr\(\ddot{o}\)dinger operators. Oper Theory Adv Appl 46:319–321

    Google Scholar 

  16. Iserles A (1994) The asymptotic behavior of certain difference equation with proportional delays. Comput Math Appl 8(1–3):141–152

    Article  MathSciNet  MATH  Google Scholar 

  17. Liu YK (1994) Asymptotic behavior of functional differential equations with proportional time delays. Eur J Appl Math 7(1):11–30

    Google Scholar 

  18. Wei J, Xu C, Zhou X, Li Q (2006) A robust packet scheduling algorithm for proportional delay differentiation services. Comput Commun 29(18):3679–3690

    Article  Google Scholar 

  19. Zhou L (2013) Dissipativity of a class of cellular neural networks with proportional delays. Nonlinear Dyn 73(3):1895–1903

    Article  MathSciNet  MATH  Google Scholar 

  20. Zhou L (2013) Delay-dependent exponential stability of cellular neural networks with multi-proportional delays. Neural Process Lett 38(3):321–346

    Article  Google Scholar 

  21. Zhou L, Chen X, Yang Y (2014) Asymptotic stability of cellular neural networks with multi-proportional delays. Appl Math Comput 229(1):457–466

    MathSciNet  MATH  Google Scholar 

  22. Zhou L (2014) Global asymptotic stability of cellular neural networks with proportional delays. Nonlinear Dyn 77(1):41–47

    Article  MathSciNet  MATH  Google Scholar 

  23. Zhou L (2015) Delay-dependent exponential synchronization of recurrent neural networks with multiple proportional delays. Neural Process Lett 42(4):619–632

    Article  Google Scholar 

  24. Zheng C, Li N, Cao J (2015) Matrix measure based stability criteria for high-order networks with proportional delay. Neurcomputing 149:1149–1154

    Article  Google Scholar 

  25. Hiena LV, Son DT (2015) Finite-time stability of a class of non-autonomous neural networks with heterogeneous proportional delays. Appl Math Comput 14:14–23

    MathSciNet  Google Scholar 

  26. Zhou L (2015) Novel global exponential stability criteria for hybrid BAM neural networks with proportional delays. Neurocomputing 161(15):99–106

    Article  Google Scholar 

  27. Zhou L, Zhang Y (2015) Global exponential stability of cellular neural networks with multi-proportional delays. Int J Biomath 8(6):1550071

    Article  MathSciNet  MATH  Google Scholar 

  28. Zhou L, Zhang Y (2016) Global exponential periodicity and stability of recurrent neural networks with multi-proportional delays. ISA Trans 60(1):89–95

    MathSciNet  Google Scholar 

  29. Zhou L, Zhang Y (2016) Global exponential stability of a class of impulsive recurrent neural networks with proportional delays via fixed point theory. J Frankl Inst 353(2):561–575

    Article  MathSciNet  Google Scholar 

  30. Wang Z, Liu Y, Yu L, Liu X (2006) Exponential stability of delayed recurrent neural networks with Markovian jumping parameters. Phys Lett A 356(4–5):346–352

    Article  MATH  Google Scholar 

  31. Wang L, Zhang Z, Wang Y (2008) Stochastic exponential stability of the delayed reaction-diffusion recurrent neural networks with Markovian jumping parameters. Phys Lett A 372(18):3201–3209

    Article  MathSciNet  MATH  Google Scholar 

  32. Liu Y, Wang Z (2009) Stability and synchronization of discrete-time Markovian jumping neural networks with mixed mode-dependent time delays. IEEE Trans Neural Netw 20(7):1102–1116

    Article  Google Scholar 

  33. Zhu Q, Yang X, Wang H (2010) Stochastically asymptotic stability of delayed recurrent neural networks with both Markovian jump parameters and nonlinear disturbances. J Frankl Inst 347(8):1489–1510

    Article  MathSciNet  MATH  Google Scholar 

  34. Vidhya C, Balasubramaniam P (2011) Robust stability of uncertain Markovian jumping stochastic Cohen–Grossberg type BAM neural networks with time-varying delays and reaction diffusion terms. Neural Parallel Sci Comput 19(1–2):181–196

    MathSciNet  MATH  Google Scholar 

  35. Balasubramaniam P, Syed M (2011) Stochastic stability of uncertain fuzzy recurrent neural networks with Markovian jumping parameters. J Comput Math 88(5):892–904

    MathSciNet  MATH  Google Scholar 

  36. Wang Y, Lin P, Wang L (2012) Exponential stability of reaction-diffusion high-order Markovian jump hopfield neural works with time-varying delays. Nonlinear Anal RWA 13(3):1353–1361

    Article  MATH  Google Scholar 

  37. Hu G, Wang K (2012) Stability in distribution of neural stochastic functional differential equations with Markovian switching. J Math Anal Appl 385:757–769

    Article  MathSciNet  MATH  Google Scholar 

  38. Han W, Liu Y, Wang LS (2012) Global exponential stability of delayed fuzzy cellular neural networks with Markovian jumping parameters. Neural Comput Appl 21(1):67–72

    Article  Google Scholar 

  39. Balasubramaniam P, Krishnasamy R, Rakkiyappan R (2012) Delay-dependent stability criterion for a class of non-linear singular Markovian jump systems with mode-dependent interval time-varying delays. Commun Nonlinear Sci 17(9):3612–3627

    Article  MathSciNet  MATH  Google Scholar 

  40. Huang H, Huang T, Chen X (2013) A mode-dependent approach to state estimation of recurrent neural networks with Markovian jumping parameters and mixed delays. Neural Netw 46:50–61

    Article  MATH  Google Scholar 

  41. Rao R, Zhong S, Wang X (2013) Delay-dependent exponential stability for Markovian jumping stochastic Cohen-Grossberg neural networks with \(p\)-Laplace diffusion and partially known transition rates via a differential inequality. Adv Differ Equ. doi:10.1186/1687-1847

    MathSciNet  Google Scholar 

  42. Raja R, Karthik Raja U, Samidurai R, Leelamani A (2013) Dissipativity of discrete-time BAM stochastic neural networks with Markovian switching and impulses. J Frankl Inst 350:3217–3247

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgments

The work is supported by the National Science Foundation of China (No. 61374009). The construction of excellent courses of ordinary differential equation in Tianjin Normal University (No. 201203).

Author information

Authors and Affiliations

  1. School of Mathematics Science, Tianjin Normal University, Tianjin, 300387, China

    Liqun Zhou

Authors
  1. Liqun Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Liqun Zhou.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhou, L. Delay-dependent exponential stability of recurrent neural networks with Markovian jumping parameters and proportional delays. Neural Comput & Applic 28 (Suppl 1), 765–773 (2017). https://doi.org/10.1007/s00521-016-2370-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-016-2370-0

Keywords

Mathematics Subject Classification

Search

Navigation