Skip to main content
Log in

Robust stability of a class of neural networks with time delays

  • Published:
Journal of Dynamics and Differential Equations Aims and scope Submit manuscript

Abstract

A stability analysis of the equilibrium position for a given class of Hopfield neural networks with time delays is presented. The robustness of the equilibrium stability with respect to variations in the time delays, system parameters, and interconnection matrix is analyzed. Three approaches are presented which account in various ways for stability of the equilibrium with respect to these perturbations.

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.

Similar content being viewed by others

References

  1. B. R. Barmish.New Tools for Robustness of Linear Systems, Macmillan, New York, 1994.

    Google Scholar 

  2. A. C. Bartlett, C. V. Hollot, and H. Lin. Root location of an entire polytope of polynomials: It suffices to check the edges.Math. Control Signals Syst. 1, 61–71, 1988.

    Google Scholar 

  3. J. Bélair. Stability in a model of a delayed neural network.J. Dynam. Diff. Eq. 5(4), 607–623, 1993.

    Google Scholar 

  4. R. Bellman and K. L. Cook.Differential-Difference Equations, Academic Press, New York, 1963.

    Google Scholar 

  5. M Fu, A. W. Olbrot, and M. P. Polis. Robust stability for time-delay systems: The edge theorem and graphical tests.IEEE Trans. AC-34, 813–820, 1989.

    Google Scholar 

  6. A. Guez, P. Protopopsecu, and J. Barhen. On the stability, storage capacity and design of nonlinear continuous neural networks.IEEE Trans. Syst. Man Cybernet. 18(1), 80–87, 1988.

    Google Scholar 

  7. D. Hinrichsen and A. J. Pritchard. Real and complex stability radii: A survey. In D. Hinrichsen and B. Mårtensson (eds.),Control of Uncertain Systems, Birkhäuser, Boston, 1990, pp. 119–162.

    Google Scholar 

  8. J. J. Hopfield. Neurons with graded response have collective computational properties like those of two-state neurons.Proc. Natl. Acad. Sci. 81 May, 3088–3092, 1984.

    Google Scholar 

  9. V. L. Kharitonov and A. P. Zhabko. Robust stability of time-delay systems.IEEE Trans. AC-39, 2388–2397, 1994.

    Google Scholar 

  10. C. M. Marcus and R. M. Westervelt. Stability of analog neural networks with delay.Phys. Rev. A 39, 347–359, 1989.

    Google Scholar 

  11. B. Morton and R. MacAfoos. A mu-test for real-parameter variations.Proc. Am. Control Conf., pp. 135–138, 1985.

  12. A. Packard and J. C. Doyle. The complex structured singular value.Automatica 29(1), 71–109, 1993.

    Google Scholar 

  13. L. S. Pontryagin. On zeros of some elementary transcendental functions.Trans. AMS Ser. 2 1, 95–100, 1955.

    Google Scholar 

  14. L. Qui, B. Bernhardsson, A. Rantzer, E. J. Davison, P. M. Young, and J. C. Doyle. On the real structured stability radius.Proc. 32nd CDC, 1993.

  15. E. D. Sontag. Neural networks for control.ECC '93 Book, 1993.

  16. N. G. Tchebotareff and N. N. Meimann. The Routh-Hurwitz problem for polynomials and entire functions.Proc. Math. Inst. Acad. Sci. USSR, 1949 (in Russian).

Download references

Author information

Authors and Affiliations

Authors

Additional information

Work conducted while visiting the University of Bremen, supported by the Deutscheforschungsgemeinschaft.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kharitonov, V.L., Paice, A.D.B. Robust stability of a class of neural networks with time delays. J Dyn Diff Equat 9, 67–91 (1997). https://doi.org/10.1007/BF02219053

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02219053

Key words

Navigation