Skip to main content

Exponential input-to-state stability of recurrent neural networks with multiple time-varying delays

Cognitive Neurodynamics volume 8, pages 47–54 (2014)Cite this article

Abstract

In this paper, input-to-state stability problems for a class of recurrent neural networks model with multiple time-varying delays are concerned with. By utilizing the Lyapunov–Krasovskii functional method and linear matrix inequalities techniques, some sufficient conditions ensuring the exponential input-to-state stability of delayed network systems are firstly obtained. Two numerical examples and its simulations are given to illustrate the efficiency of the derived results.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  • Ahn CK (2010a) An H∞ approach to stability analysis of switched Hopfield neural networks with time-delay. Nonlinear Dyn 60(4): 703–711

    Article  Google Scholar 

  • Ahn CK (2010b) Passive learning and input-to-state stability of switched Hopfiled neural networks with time-delay. Inf Sci 180: 4582–4594

    Article  Google Scholar 

  • Ahn CK (2010c) \(L_2-L_\infty\) nonlinear system identification via recurrent neural networks. Nonlinear Dyn 62:543–552

  • Ahn CK (2011a) Some new results on stability of Takagi-Sugeno fuzzy Hopfield neural networks. Fuzzy Sets Syst 179: 100–111

    Article  Google Scholar 

  • Ahn CK (2011b) Robust stability of recurrent neural networks with ISS learning algorithm. Nonliear Dyn 65:413–419

    Article  Google Scholar 

  • Ahn CK (2012a) Switched exponential state estimation of neural networks based on passivity theory. Nonlinear Dyn 67(1): 573–586

    Article  Google Scholar 

  • Ahn CK (2012b) Linear matrix inequality optimization approach to exponential robust filtering for switched Hopfield neural networks. J Optim Theory Appl 154 (2): 573–587

    Article  Google Scholar 

  • Ahn CK (2012c) An error passivation approach to filtering for switched neural networks with noise disturbance. Neural Comput Appl 21 (5): 853–861

    Article  Google Scholar 

  • Angeli D, Sontag ED, Wang Y (2000) A characterization of integral input to state stability. IEEE Trans Automat Contr 45: 1082–1097

    Article  Google Scholar 

  • Arik S (2000) Stability analysis of delayed neural networks. IEEE Trans Cricuits Syst I: Fund Theory Appl 47: 1089–1092

    Article  Google Scholar 

  • Ensari T, Arik S (2005) Global stability analysis of neural networks with multiple time-varying delays. IEEE Trans Autom Contr 50: 1781–1785

    Article  Google Scholar 

  • Grujiá LT, Michel AN (1991) Exponential stability and trajectory bands of neural networks under structural variations. IEEE Trans Cricuits Syst 38: 1182–1192

    Article  Google Scholar 

  • Hong YG, Jiang ZP, Feng G(2010) Finite-time input-to-state stability and applications to finite-time control design. SIAM J Contr Optim 48: 4395–4418

    Article  Google Scholar 

  • Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two state neurons. Proc Natl Acad Sci USA 81: 3088–3092

    CAS  PubMed  Article  Google Scholar 

  • Hopfield JJ, Tank DW (1986) Computing with neural networks: a model. Science (New Series) 233: 625–633

    CAS  Article  Google Scholar 

  • Horn RA, Johnson CR (1991) Topics in matrix analysis. Cambridge University Press, London

    Book  Google Scholar 

  • Huang H, Feng G (2009) Delay-dependent H∞ and generalized filtering H 2 for delayed neural networks. IEEE Trans Circuits Syst I: Reg Pap 56(4): 846–857

    Article  Google Scholar 

  • Huang T, Li C, Duan S, Starzyk J (2012) Robust exponential stability of uncertain delayed neural networks with stochastic perturbation and impulse effects. IEEE Trans Neural Netw Learn Syst 23: 866–875

    Article  Google Scholar 

  • Jiang ZP, Wang Y (2001) Input-to-state stability for discrete-time nonliear systems. Automatica 37: 857-89

    Article  Google Scholar 

  • Liu X, Cao J (2010) Robust state estimation for neural networks with discontinuous activations. IEEE Trans Syst Man Cybern Part B Cybern 40(6): 1083–4419

    Google Scholar 

  • Matsouka K (1992) Stability conditions for nonlinear continuous neural networks with asymmetric connections weights. Neural Netw 5: 495–500

    Article  Google Scholar 

  • Sanchez EN, Perez JP (1999) Input-to-state stability (ISS) analysis for dynamical neural networks. IEEE Trans Circuits Syst I: Fundam Theorem Appl 46: 1395–1398

    Article  Google Scholar 

  • Sontag ED (1989) Smooth stabilition implies corprime factorization. IEEE Trans Autom Contr 34: 435–443

    Article  Google Scholar 

  • Sontag ED (1990) Further facts about input-to-state stabilization. IEEE Trans Autom Contr 35: 473–476

    Article  Google Scholar 

  • Sontag ED, Wang Y (1995) On characterizations of the input-to-state stability property. Syst Contr Lett 24: 351–359

    Article  Google Scholar 

  • Wu H, Feng W, Liang X (2008) New stability criteria for uncertain neural networks with interval time-varying delays. Cogn Neurodyn 2(4): 363–370

    PubMed Central  PubMed  Article  Google Scholar 

  • Wu X, Wang Y, Huang L, Zuo Y (2010) Robust stability analysis of delayed Takagi-Sugeno fuzzy Hopfield neural networks with discontinuous activation functions. Cogn Neurodyn 4(4): 347–354

    PubMed Central  PubMed  Article  Google Scholar 

  • Yang ZC, Hong YG (2012a) Stabilization of impulsive hybrid systems using quantized input and output feedback. Asian J Contr 14: 679–692

    Article  Google Scholar 

  • Yang ZC, Zhou WS (2012b) Input-to-state stability of impulsive hybrid systems with stochastic effects. In Proceedings of the 24th IEEE China conference on decision and control pp 286–291

  • Zhang HG, Wang ZS, Liu DR (2008) Global asymptotic stability of recurrent neural networks with multiple time-varying delays. IEEE Trans Neural Netw 19: 855–873

    PubMed  Article  Google Scholar 

  • Zhu S, Shen Y (2012) Two algebraic criteria for input-to-state stability of recurrent neural networks with time-varying delays. Neural Comput Appl. doi 1007/s00521-012-0882-9

Download references

Acknowledgments

The work is supported partially by National Natural Science Foundation of China under Grant No.10971240, National Priority Research Project of Qatar under Grant No.4-451-2-168 and No.4-1162-1-181, Key Project of Chinese Education Ministry under Grant No.212138, the Program of Chongqing Innovation Team Project in University under Grant No.KJTD201308, Natural Science Foundation of Chongqing under Grant CQ CSTC 2011BB0117, Foundation of Science and Technology project of Chongqing Education Commission under Grant KJ120630. We also would like to thank the referee for valuable suggestions.

Author information

Affiliations

  1. Department of Mathematics, Key Laboratory for Optimization and Control of Ministry of Education, Chongqing Normal University, Chongqing, 400047, China

    Zhichun Yang

  2. Department of Mathematics, Chongqing Normal University, Chongqing, 400047, China

    Weisong Zhou

  3. Texas A&M University at Qatar, PO Box 23874, Doha, Qatar

    Tingwen Huang

Authors
  1. Zhichun Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Weisong Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tingwen Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhichun Yang.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Yang, Z., Zhou, W. & Huang, T. Exponential input-to-state stability of recurrent neural networks with multiple time-varying delays. Cogn Neurodyn 8, 47–54 (2014). https://doi.org/10.1007/s11571-013-9258-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11571-013-9258-9

Keywords

  • Exponential input-to-state stability (exp-ISS)
  • Recurrent neural networks
  • Multiple time-varying delays