Skip to main content
SpringerLink
Log in

Exponential input-to-state stability of stochastic neural networks with mixed delays

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

This paper is concerned with the exponential input-to-state stability for a class of stochastic neural networks with mixed delays. Based on a new Lyapunov-Krasovskii functional, Itô’s formula, Dynkin’s formula and some inequality techniques, some novel sufficient conditions ensuring the exponential input-to-state stability in the mean square for the given stochastic neural networks are derived. Some existing results are extended. Two numerical examples are provided to illustrate the effectiveness of the proposed method.

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
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Beaufay F, Abdel-Magrid Y, Widrow B (1994) Application of neural networks to load-frequency control in power systems. Neural Networks 7(1):183–194

    Article  Google Scholar 

  2. Galicki M, Witte H, Dorschel J, Eiselt M, Griessbach G (1997) Common optimization of adaptive preprocessing units and a neural network during the learning period, Application in EEG pattern recognition. Neural Networks 10(6):1153–1163

    Article  Google Scholar 

  3. Wong BK, Selvi Y (1998) Neural network applications in finance: a review and analysis of literature(1990–1996). Info Manag 34(3):129–139

    Article  Google Scholar 

  4. Tian J, Xiong W, Xu F (2014) Improved delay-partitioning method to stability analysis for neural networks with discrete and distributed time-varying delays. Appl Math Comput 233:152–164

    MathSciNet  MATH  Google Scholar 

  5. Zhou X, Tian J, Ma H, Zhong S (2014) Improved delay-dependent stability criteria for recurrent neural networks with time-varying delays. Neurocomputing 129:401–408

    Article  Google Scholar 

  6. Liu X-G, Tang M-L, Martin RR, Liu XB (2007) Discrete-time BAM neural networks with variable delays. Phys Lett A 367:322–330

    Article  MATH  Google Scholar 

  7. Liu X-G, Martin RR, Wu M, Tang M-L (2008) Global exponential stability of bidirectional associative memory neural networks with time delays. IEEE Trans Neural Networks 19(3):397–407

    Article  Google Scholar 

  8. Shi L, Zhu H, Zhong S, Hou L (2013) Globally exponential stability for neural networks with time-varying delays. Appl Math Comput 219(21):10487–10498

    MathSciNet  MATH  Google Scholar 

  9. Kwon OM, Park JH, Lee SM, Cha EJ (2012) New approaches on stability criteria for neural networks with interval time-varying delays. Appl Math Comput 218(19):9953–9964

    MathSciNet  MATH  Google Scholar 

  10. Kwon OM, Park JH, Lee SM, Cha EJ (2014) New and improved results on stability of static neural networks with interval time-varying delays. Appl Math Comput 239:346–357

    MathSciNet  MATH  Google Scholar 

  11. Kwon OM, Park JH, Lee SM, Cha EJ (2013) Analysis on delay-dependent stability for neural networks with time-varying delays. Neurocomputing 103:114–120

    Article  Google Scholar 

  12. Zhang X, Han Q (2009) New Lyapunov-Krasovskii functionals for global asymptotic stability of delayed neural networks. IEEE Trans Neural Networks 20(3):533–539

    Article  Google Scholar 

  13. Zhang X, Han Q (2011) Global asymptotic stability for a class of generalized neural networks with interval time-varying delays. IEEE Trans Neural Networks 22(8):1180–1192

    Article  Google Scholar 

  14. Zhang X, Han Q (2014) Global asymptotic stability analysis for delayed neural networks using a matrix quadratic convex approach. Neural Networks 54:57–69

    Article  MATH  Google Scholar 

  15. Liu X, Wang F, Shu Y (2016) A novel summation inequality for stability analysis of discrete-time neural networks. J Comput Appl Math 304:160–171

    Article  MathSciNet  MATH  Google Scholar 

  16. Rakkiyappan R, Chandrasekar A, Lakshmanan S, Park JH, Jung H (2013) Effects of leakage time-varying delays in Markovian jump neural networks with impulse control. Neurocomputing 121:365–378

    Article  Google Scholar 

  17. Yang Z, Zhou W, Huang T (2014) Exponential input-to-state stability of recurrent neural networks with multiple time-varying delays. Cognitive Neurodyn 8(1):47–54

    Article  Google Scholar 

  18. Ahn CK (2010) Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay. Infor Sci 180(23):4582–4594

    Article  MATH  Google Scholar 

  19. 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):680–686

    MathSciNet  MATH  Google Scholar 

  20. Zhang Y, He Y, Wu M (2009) Delay-dependent robust stability for uncertain stochastic systems with interval time-varying delay. Acta Automatica Sinica 35(5):577–582

    Article  MathSciNet  MATH  Google Scholar 

  21. Ma Q, Xu S, Zou Y, Lu J (2011) Stability of stochastic Markovian jump neural networks with mode-dependent delays. Neurocomputing 74(12):2157–2163

    Article  Google Scholar 

  22. Ning C, He Y, Wu M, Liu Q (2012) Pth moment exponential stability of neutral stochastic differential equations driven by Lévy noise. J Franklin Inst 349(9):2925–2933

    Article  MathSciNet  MATH  Google Scholar 

  23. Zhu Q, Li X (2012) Exponential and almost sure exponential stability of stochastic fuzzy delayed Cohen-Grossberg neural networks. Fuzzy Sets Syst 203:74–94

    Article  MathSciNet  MATH  Google Scholar 

  24. Ali MS (2014) Robust stability of stochastic uncertain recurrent neural networks with Markovian jumping parameters and time-varying delays. Int J Mach Learn Cybernet 5:13–22

    Article  Google Scholar 

  25. Zhang X, Han Q (2015) On designing network-based H-infinity controllers for stochastic systems. Int J Robust Nonlinear Control 25(1):52–71

    MathSciNet  MATH  Google Scholar 

  26. Zhu Q, Cao J (2011) Exponential stability of stochastic neural networks with both Markovian jump parameters and mixed time delays. IEEE Trans Syst Man Cybernet Part B Cybernet 41(2):341–353

    Google Scholar 

  27. Pan L, Cao J (2012) Robust stability for uncertain stochastic neural networks with delays and impulses. Neurocomputing 94:102–110

    Article  Google Scholar 

  28. Zhu Q, Cao J (2010) Robust exponential stability of Markovian impulsive stochastic Cohen-Grossberg neural networks with mixed time delays. IEEE Trans Neural Networks 21(8):1314–1325

    Article  Google Scholar 

  29. Rakkiyappan R, Chandrasekar A, Lakshmanan S, Park JH (2014) Exponential stability of Markovian jumping stochastic Cohen-Grossberg neural networks with mode-dependent probabilistic time-varying delays and impulses. Neurocomputing 131:265–277

    Article  Google Scholar 

  30. Rakkiyappan R, Chandrasekar A, Lakshmanan S, Park JH (2015) Exponential stability for Markovian jumping stochastic BAM neural networks with mode-dependent probabilistic time-varying delays and impulse control. Complexity 20(3):39–65

    Article  MathSciNet  Google Scholar 

  31. Sontag ED (1989) Smooth stabilization implies coprime factorization. IEEE Trans Auto Control 34(4):435–443

    Article  MathSciNet  MATH  Google Scholar 

  32. Xu Y, Luo W, Zhong K, Zhu S (2014) Mean square input-to-state stability of a general class of stochastic recurrent neural networks with Markovian switching. Neural Comput Appl 25(7–8):1657–1663

    Article  Google Scholar 

  33. Zhou W, Teng L, Xu D (2015) Mean-square exponential input-to-state stability of stochastic Cohen-Grossberg neural networks with time-varying delays. Neurocomputing 153:54–61

    Article  Google Scholar 

  34. Zhu Q, Cao J, Rakkiyappan R (2015) Exponential input-to-state stability of stochastic Cohen-Grossberg neural networks with mixed delays. Nonlinear Dyn 79(2):1085–1098

    Article  MathSciNet  MATH  Google Scholar 

  35. Zhu Q, Cao J (2014) Mean-square exponential input-to-state stability of stochastic delayed neural networks. Neurocomputing 131:157–163

    Article  Google Scholar 

  36. Halanay A (1966) Differential Equations: Stability, Oscillations, Time lags. Academic Press, New York

    MATH  Google Scholar 

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

    Article  Google Scholar 

  38. Kwon OM, Lee SM, Park JH (2010) Improved delay-dependent exponential stability for uncertain stochastic neural networks with time-varying delays. Phys Lett A 374:1232–1241

    Article  MATH  Google Scholar 

  39. Tang Z, Feng J, Zhao Y (2015) Global synchronization of nonlinear coupled complex dynamical networks with information exchanges at discrete-time. Neurocomputing 151:1486–1494

    Article  Google Scholar 

  40. Park MJ, Kwon OM, Park JH, Lee SM, Cha EJ (2014) Synchronization of discrete-time complex dynamical networks with interval time-varying delays via non-fragile controller with randomly occurring perturbation. J Franklin Inst 351:4850–4871

    Article  MathSciNet  Google Scholar 

  41. Wang XZ (2015) Learning from big data with uncertainty-editorial. J Intell Fuzzy Syst 28(5):2329–2330

    Article  MathSciNet  Google Scholar 

  42. Wang XZ, Ashfaq RAR, Fu AM (2015) Fuzziness based sample categorization for classifier performance improvement. J Intell Fuzzy Syst 29(3):1185–1196

    Article  MathSciNet  Google Scholar 

  43. He YL, Wang XZ, Huang JZX (2016) Fuzzy nonlinear regression analysis using a random weight network. Info Sci 364–365:222–240

    Article  Google Scholar 

  44. He YL, Liu JNK, Hu YX, Wang XZ (2015) OWA operator based link prediction ensemble for social network. Expert Syst Appl 42(1):21–50

    Article  Google Scholar 

  45. Ashfaq RAR, Wang XZ, Huang JZX, Abbas H, He YL (2016) Fuzziness based semi-supervised learning approach for Intrusion Detection System. Info Sci (in press), doi:10.1016/j.ins.2016.04.019

Download references

Acknowledgments

This work is partly supported by NSFC under grant Nos.61271355 and 61375063 and the ZNDXYJSJGXM under grant No. 2015JGB21. Moreover, we appreciate very much the advice of the reviewers.

Author information

Authors and Affiliations

  1. School of Mathematics and Statistics, Central South University, Changsha, 410083, Hunan, China

    Yan-Jun Shu, Xin-Ge Liu, Feng-Xian Wang & Sai-Bing Qiu

Authors
  1. Yan-Jun Shu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xin-Ge Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Feng-Xian Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sai-Bing Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xin-Ge Liu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shu, YJ., Liu, XG., Wang, FX. et al. Exponential input-to-state stability of stochastic neural networks with mixed delays. Int. J. Mach. Learn. & Cyber. 9, 807–819 (2018). https://doi.org/10.1007/s13042-016-0609-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-016-0609-9

Keywords

Search

Navigation