Skip to main content
Springer Nature Link
Log in

Complete Convergence of Competitive Neural Networks with Different Time Scales

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

This paper studies the complete convergence of a class of neural networks with different time scales under the assumption that the activation functions are unsaturated piecewise linear functions. Under this assumption, there are multiple equilibrium points in the neural network. Traditional methods cannot be used in this neural network. Complete convergence is proved by constructing an energy-like function. Simulations are employed to illustrate the theory.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • S. Amari (1983) ArticleTitleField theory of self-organizing neural nets IEEE Transactions System Man Cybernetics SMC 13 741–748

    Google Scholar 

  • R. Douglas C. Koch M. Mahowald K. Martin H. Suarez (1995) ArticleTitleRecurrent excitation in neocortical circuits Science 269 981–985

    Google Scholar 

  • S. Grossberg (1978) ArticleTitleCompetition, decision and consensus Journal of Mathematical and Analytical and Applications 66 470–493

    Google Scholar 

  • R. Hahnloser (1998) ArticleTitleOn the piecewise analysis of linear threshold neural networks Neural Networks 11 691–697

    Google Scholar 

  • R. Hahnloser M. A. Mahowald R. J. Douglas H.S. Seung (2000) ArticleTitleDigitial selection and analogue amplification coexist in a cortex inspired silicon circuit Nature 405 947–951

    Google Scholar 

  • R. Hahnloser H. S. Seung J. J. Slotine (2003) ArticleTitlePermitted and forbidden sets in symmetric threshold-linear networks Neural Computation 15 621–638

    Google Scholar 

  • M. Lemmon V. Kumar (1989) ArticleTitleEmulating the dynamics for a class of laterally inhibited neural networks Neural Networks 2 193–214

    Google Scholar 

  • A. Meyer-Baese S. S. Pilyugin Y. Chen (2003) ArticleTitleGlobal exponential stability of competitive neural networks with differernt time scales IEEE Transactions Neural Network 14 IssueID3 716–719

    Google Scholar 

  • A. Meyer-Base F. Ohl H. Scheich (1996) ArticleTitleSingular perturbation annalysis of competitve neural networks with different time scales Neural Computation 8 545–563

    Google Scholar 

  • H. Wersing W. J. Beyn H. Ritter (2001) ArticleTitleDynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions Neural Computation 13 1811–1825

    Google Scholar 

  • X. Xie R. Hahnloser H. S. Seung (2002) ArticleTitleSelectively grouping neurons in recurrent networks of lateral inhibition Neural Computation 14 2627–2646

    Google Scholar 

  • Z. Yi K. K. Tan T. H. Lee (2003) ArticleTitleMultistablity analysis for recurrent neural networks with unsaturating piecewise linear transfer functions Neural Computation 15 639–662

    Google Scholar 

  • Z Yi K. Tan (2003) Convergence Analysis of Recurrent Neural Networks Kluwer Academic Publishers Dordrecht

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, 210016, Nanjing, PR China

    Mao Ye & Yi Zhang

  2. Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, 610054, Chengdu, P.R. China

    Mao Ye

Authors
  1. Mao Ye
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yi Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Mao Ye.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ye, M., Zhang, Y. Complete Convergence of Competitive Neural Networks with Different Time Scales. Neural Process Lett 21, 53–60 (2005). https://doi.org/10.1007/s11063-004-3427-0

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-004-3427-0

Keywords