Skip to main content
SpringerLink
Log in

Analysis of the convergency of topology preserving neural networks on learning

  • Conference paper
  • First Online:
Book cover Algorithms and Computation (ISAAC 1994)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 834))

Included in the following conference series:

  • 135 Accesses

Abstract

In this paper, a general conclusion for verifying the convergency of topology preserving neural networks is presented, by which the networks are proven to produce convergent feature maps for uniformly distributed inputs. As a special example, the Kohonen's self organizing networks are also proven to be convergent. This paper revises and extends the products in existance and provids a new method for further studying the convergence properties of self organizing neural networks.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. T. Kohonen, Self-organized formation of topologically correct feature maps, Biol. Cybern. vol.43 pp.203–243, 1982.

    Article  Google Scholar 

  2. T. Kohonen, Analysis of simple self-organizing process, Biol. Cybern., vol. 44, pp.135–140, 1982.

    Article  Google Scholar 

  3. M. Contrell and J.C. Fort, A stochastic model of retinotopy: A self organizing process, Biol. Cybern., vol. 53, pp.405–411, 1986.

    PubMed  Google Scholar 

  4. -, Etude d'un processus d'auto-organization, Ann. Inst. Henri Poincare, vol. 23, no. 1, pp. 1–20, 1987.

    Google Scholar 

  5. H. Ritter and K. Schulten, On the stationary state of Kohonen's self-organizing sensory mapping, Biol. Cybern., vol.54, pp. 99–106, 1986.

    Article  Google Scholar 

  6. V. Tolat, An analysis of Kohonen's self-organizingmaps using a system of energy functions, Biol. Cybern., vol. 65, pp. 155–164, 1990.

    Google Scholar 

  7. Z.P. Lo and B. Bavarian, On the rate of convergence in topology preserving neural networks, Biol. Cybern., vol. 65, pp.55–63, 1991.

    PubMed  MathSciNet  Google Scholar 

  8. Z.P. Lo, Y. Yu and B. Bavarian, Analysis of the convergence properties of topology preserving neural networks, IEEE Trans. on N. Networks, vol.4, no.2, pp. 207–220, 1993.

    Article  Google Scholar 

  9. H.-F. Chen, Recursive Estimation and Contol for Stochastic system. New York: Wiley 1985.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dept. of Computer Science, Shandong Univ., postcode:250100, China

    Zhu Daming, Ma Shaohan & Qiu Hongze

Authors
  1. Zhu Daming
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ma Shaohan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qiu Hongze
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Ding-Zhu Du Xiang-Sun Zhang

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Daming, Z., Shaohan, M., Hongze, Q. (1994). Analysis of the convergency of topology preserving neural networks on learning. In: Du, DZ., Zhang, XS. (eds) Algorithms and Computation. ISAAC 1994. Lecture Notes in Computer Science, vol 834. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58325-4_174

Download citation

  • DOI: https://doi.org/10.1007/3-540-58325-4_174

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-58325-7

  • Online ISBN: 978-3-540-48653-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation