Skip to main content
SpringerLink
Log in

Passivity Analysis of Dynamic Neural Networks with Different Time-scales

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Dynamic neural networks with different time-scales include the aspects of fast and slow phenomenons. Some applications require that the equilibrium points of the designed networks are stable. In this paper, the passivity-based approach is used to derive stability conditions for dynamic neural networks with different time-scales. Several stability properties, such as passivity, asymptotic stability, input-to-state stability and bounded input bounded output stability, are guaranteed in certain senses. A numerical example is also given to demonstrate the effectiveness of the theoretical 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

Similar content being viewed by others

References

  1. Amari S. (1982) Competitive and cooperative aspects in dynamics of neural excitation and self-organization. Competition Cooperation Neural Networks 20, 1–28

    ADS  Google Scholar 

  2. Byrnes C.I., Isidori A., Willems J.C. (1991) Passivity, feedback equivalence, and the global stabilization of minimum phase nonlinear systems. IEEE Transaction Automatic Control 36, 1228–1240

    Article  MATH  MathSciNet  Google Scholar 

  3. Commuri S., Lewis F.L. (1996) CMAC neural networks for control of nonlinear dynamical systems: structure, stability and passivity. Automatica 33(4): 635–641

    Article  MathSciNet  Google Scholar 

  4. Forti M., Manetti S., Marini M. (1994) Necessary and sufficient condition for absolute stability of neural networks. IEEE Transactions on Circuit and Systems-I 41, 491–494

    Article  MATH  MathSciNet  Google Scholar 

  5. Grossberg S. (1976) Adaptive pattern classification and universal recording. Biological Cybernetics 23, 121–134

    Article  MathSciNet  Google Scholar 

  6. Hopfield J.J. (1984) Neurons with grade response have collective computational properties like those of a two-state neurons. Proceedings of the National Academy of Science USA 81: 3088–3092

    Article  ADS  Google Scholar 

  7. Jagannathan S., Lewis F.L. (1996), Identification of nonlinear dynamical systems using multilayered neural networks. Automatica 32(12): 1707–1712

    Article  MATH  MathSciNet  Google Scholar 

  8. Jin L., Gupta M. (1999), Stable dynamic backpropagation learning in recurrent neural networks. IEEE Transactions on Neural Networks 10: 1321–1334

    Article  Google Scholar 

  9. Kaszkurewics K., Bhaya A. (1994) On a class of globally stable neural circuits. IEEE Transactions on Circuit and Systems-I 41, 171–174

    Article  Google Scholar 

  10. Khalil H.K. Nonlinear Systems, 2nd ed. Prentice-Hall, Inc., 1996

  11. Kosmatopoulos E.B., Polycarpou M.M., Christodoulou M.A., Ioannpu P.A. (1995) High-order neural network structures for identification of dynamical systems. IEEE Transactions on Neural Networks 6(2): 442–431

    Article  Google Scholar 

  12. Lemmon M., Kumar V. (1995) Emulating the dynamics for a class of laterally inhibited neural networks. Neural Networks 2, 193–214

    Article  Google Scholar 

  13. Lewis F.L., Liu K., Yesildirek A. (1996) Multilayer neural-net robot controller with guaranteed tracking performance. IEEE Transactions on Neural Network 7(2): 388–398

    Article  Google Scholar 

  14. Liu H., Sun F., Sun Z. (2005) Stability analysis and synthesis of fuzzy singularly perturbed systems. IEEE Transactions on Fuzzy Systems 13(2): 273–284

    Article  Google Scholar 

  15. Lu H., He Z. (2005), Global exponential stability of delayed competitive neural networks with different time scales. Neural Networks 18(3): 243–250

    Article  MATH  Google Scholar 

  16. Maa C.Y., Shanblatt M.A. (1992), Linear and quadratic programming neural network analysis. IEEE Transaction Neural Networks 3(4): 580–594

    Article  Google Scholar 

  17. Matsouka K. (1992), Stability conditions for nonlinear continuous neural networks with asymmetric connection weights. Neural Networks 5, 495–500

    Article  Google Scholar 

  18. Meyer-Bäse A., Ohl F., Scheich H. (1996) Singular perturbation analysis of competitive neural networks with different time-scales. Neural Computation 8, 545–563

    Google Scholar 

  19. Meyer-Baese A., Pilyugin S.S., Chen Y. (2003) Global exponential stability of competitive neural networks with different time scales. IEEE Transactions on Neural Networks 14(3): 716–719

    Article  Google Scholar 

  20. Poznyak A.S., Sanchez E.N. and Yu W.: Differential Neural Networks for Robust Nonlinear Control, Singapore: World Scientific Publishing Co., 2001

  21. Rovithakis A. (2004) Robust redesign of a neural network controller in the presence of unmodelled dynamics. IEEE Transactions on Neural Networks 15(6): 1482–1490

    Article  Google Scholar 

  22. Rovithakis A., Christodoulou M.A. (1994) Adaptive control of unknown plants using dynamical neural networks. IEEE Transactions on Systems Man and Cybernetics 24, 400–412

    Article  MathSciNet  Google Scholar 

  23. Sepulchre R., Jankovic M., Kokotovic P.V., (1997) Constructive Nonlinear Control. London, Springer-Verlag

    MATH  Google Scholar 

  24. Sontag E.D., Wang Y. (1995) On characterization of the input-to-state stability property. System & Control Letters 24, 351–359

    Article  MATH  MathSciNet  Google Scholar 

  25. Suykens J., Moor B., Vandewalle J. (2000) Robust local stability of multilayer recurrent neural networks. IEEE Transactions Neural Networks 11, 222–229

    Article  Google Scholar 

  26. Ye M., Zhang Y. (2005) Complete convergence of competitive neural networks with different time scales. Neural Processing Letters 21(1): 53–60

    Article  Google Scholar 

  27. Yu W. (2003) Passivity analysis for dynamic multilayer neuro identifier. IEEE Transactions on Circuits and Systems Part I, 50(1): 173–178

    Article  Google Scholar 

  28. Yu W., Li X. (2001) Some stability properties of dynamic neural networks. IEEE Transactions on Circuits and Systems Part I, 48(2): 256–259

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Departamento de Control Automatico, CINVESTAV-IPN, A.P. 14-740, Av.IPN 2508, México, D.F., 07360, México

    Wen Yu

  2. Departamento de Computación, CINVESTAV-IPN, A.P. 14-740, Av.IPN 2508, México, D.F., 07360, México

    Xiaoou Li

Authors
  1. Wen Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoou Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wen Yu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Yu, W., Li, X. Passivity Analysis of Dynamic Neural Networks with Different Time-scales. Neural Process Lett 25, 143–155 (2007). https://doi.org/10.1007/s11063-007-9034-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-007-9034-0

Keywords

Search

Navigation