Skip to main content
Log in

On Global Robust Stability of a Class of Delayed Neural Networks with Discontinuous Activation Functions and Norm-Bounded Uncertainty

  • Published:
Circuits, Systems, and Signal Processing Aims and scope Submit manuscript

Abstract

This paper considers the problem of global robust stability of a class of uncertain delayed neural networks with discontinuous activation functions. The uncertainties are assumed to be norm-bounded. In the form of linear matrix inequality (LMI), a new sufficient condition is obtained for the robust stability of this class of neural networks based on Lyapunov–Krasovskii stability theory as well as Filippov theory. Our conditions are independent of the delay and easy to check. A numerical example is given to show the effectiveness and superiority of our results.

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

Similar content being viewed by others

References

  1. J. Aubin, A. Cellina, Differential Inclusions (Springer, Berlin, 1984)

    MATH  Google Scholar 

  2. A. Baciotti, R. Conti, P. Marcellini, Discontinuous ordinary differential equations and stabilization. Universita di Firenze (2000)

  3. S. Boyd, L. Ghaoui, E. Feron, V. Balakrishnan, Linear Matrix Inequalities in System and Control Theory (SIAM, Philadelphia, 1994)

    MATH  Google Scholar 

  4. J. Cao, J. Wang, Global asymptotic and robust stability of recurrent neural networks with time delays. IEEE Trans. Circ. Syst. I, Regul. Pap. 52(3), 417–426 (2005)

    MathSciNet  Google Scholar 

  5. F. Clarke, Optimization and Nonsmooth Analysis (Wiley, New York, 1994)

    Google Scholar 

  6. A. Filippov, Differential Equations with Discontinuous Right-Hand Side (Kluwer Academic, Boston, 1988)

    Google Scholar 

  7. M. Forti, P. Nistri, Global convergence of neural networks with discontinuous neuron activations. IEEE Trans. Circ. Syst. 1, Fundam. Theory Appl. 50(11), 1421–1435 (2003)

    Article  MathSciNet  Google Scholar 

  8. M. Forti, P. Nistri, Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain. IEEE Trans. Neural Netw. 16(6), 1449–1463 (2005)

    Article  Google Scholar 

  9. M. Forti, M. Grazzini, P. Nistri, L. Pancioni, Generalized Lyapunov approach for convergence of neural networks with discontinuous or non-Lipschitz activations. IEEE Trans. Neural Netw. 214(6), 88–99 (2006)

    MATH  MathSciNet  Google Scholar 

  10. Z. Guo, L. Huang, LMI conditions for global robust stability of delayed neural networks with discontinuous neuron activations. Appl. Math. Comput. 215(3), 889–900 (2009)

    Article  MATH  MathSciNet  Google Scholar 

  11. J. Hale, Ordinary Differential Equations (Wiley, New York, 1994)

    Google Scholar 

  12. P. Li, J. Cao, Stability in static delayed neural networks: a nonlinear measure approach. Neurocomputing 69(15), 1776–1781 (2006)

    Article  MathSciNet  Google Scholar 

  13. W. Lu, T. Chen, Dynamical behaviors of Cohen–Grossberg neural networks with discontinuous activation functions. Neural Netw. 18(3), 231–242 (2005)

    Article  MATH  Google Scholar 

  14. W. Lu, T. Chen, Dynamical behaviors of delayed neural network systems with discontinuous activation functions. Neural Comput. 18(1), 683–708 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  15. D. Papini, V. Taddei, Global exponential stability of the periodic solution of a delayed neural network with discontinuous activations. Phys. Lett. A 343(2), 117–128 (2005)

    Article  MATH  Google Scholar 

  16. H. Qi, New sufficient conditions for global robust stability of delayed neural networks. IEEE Trans. Circ. Syst. I, Regul. Pap. 18(1), 683–708 (2006)

    Google Scholar 

  17. H. Qi, Global robust stability of delayed neural networks. IEEE Trans. Circ. Syst. I, Fundam. Theory Appl. 50(1), 156–160 (2003)

    Article  Google Scholar 

  18. V. Singh, Robust stability of cellular neural networks with delay: linear matrix inequality approach. IEE Proc. Control Theory Appl. 151(1), 125–129 (2004)

    Article  Google Scholar 

  19. V. Singh, Novel LMI condition for global robust stability of delayed neural networks. Chaos Solition Fractals 34(4), 503–508 (2007)

    Article  MATH  Google Scholar 

  20. V. Singh, LMI approach to the global robust stability of a larger class of neural networks with delay. Chaos Solition Fractals 32(4), 1927–1934 (2007)

    Article  MATH  Google Scholar 

  21. Y. Wang, Y. Zuo, L. Huang, C. Li, Global robust stability of delayed neural networks with discontinuous activation functions and interval uncertainties. IET Control Theory Appl. 2(7), 543–553 (2008)

    Article  MathSciNet  Google Scholar 

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

    Article  MATH  Google Scholar 

  23. Z. Wang, H. Shu, J. Fang, X. Liu, Robust stability for stochastic Hopfield neural networks with time delays. Nonlinear Anal.: Real World Appl. 7(5), 1119–1128 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  24. Z. Wang, L. Huang, Y. Wang, Robust decentralized adaptive control for a class of uncertain neural networks with time-varying delays. Appl. Math. Comput. 215(12), 4154–4163 (2010)

    Article  MATH  MathSciNet  Google Scholar 

  25. X. Wu, Y. Wang, L. Huang, Y. Zuo, Robust exponential stability criterion for uncertain neural networks with discontinuous activation functions and time-varying delays. Neurocomputing (2010). doi:10.1016/j.neucom.2010.01.002

  26. L. Xie, M. Fu, D. Souza, H control and quadratic stabilization of systems with parameter uncertainty via output feedback. IEEE Trans. Autom. Control 37(8), 1253–1256 (1992)

    Article  Google Scholar 

  27. S. Xu, J. Lam, D. Ho, Y. Zou, Improved global robust asymptotic stability criteria for delayed cellular neural networks. IEEE Trans. Syst. Man Cybern. Part B: Cybern. 35(6), 1317–1321 (2005)

    Article  Google Scholar 

  28. Q. Zhang, X. Wei, J. Xu, A new global stability result for delayed neural networks. Nonlinear Anal.: Real World Appl. 8(3), 1024–1028 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  29. W. Zhu, J. Hu, Stability analysis of stochastic delayed cellular neural networks by LMI approach. Chaos Solition Fractals 29(1), 171–174 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  30. Y. Zuo, Y. Wang, L. Huang, Z. Wang, X. Liu, C. Li, Robust stability criterion for delayed neural networks with discontinuous activation functions. Neural Process Lett. 29(1), 29–44 (2009)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yi Zuo.

Additional information

This work was supported by National Natural Science Foundation of China (10771055, 60775047, 60835004), Research Foundation of Hunan Provincial Education Department (10C0356), Graduate Innovation Foundation of Hunan Province (521298297[08], CX2009B065, 2010) and National High Technology Research and Development Program of China (863 Program: 2007AA04Z244, 2008AA04Z214). Some of the work was done in Canada when the author Yi Zuo visited the University of Waterloo.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zuo, Y., Wang, Y., Zhang, Y. et al. On Global Robust Stability of a Class of Delayed Neural Networks with Discontinuous Activation Functions and Norm-Bounded Uncertainty. Circuits Syst Signal Process 30, 35–53 (2011). https://doi.org/10.1007/s00034-010-9206-4

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00034-010-9206-4

Keywords

Navigation