Be Busy and Unique — or Be History—The Utility Criterion for Removing Units in Self-Organizing Networks | SpringerLink
Skip to main content
Springer Nature Link
Log in

Be Busy and Unique — or Be History—The Utility Criterion for Removing Units in Self-Organizing Networks

  • Conference paper
  • First Online:
KI-99: Advances in Artificial Intelligence (KI 1999)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1701))

Included in the following conference series:

  • 529 Accesses

Abstract

A novel on-line criterion for identifying “useless” neurons of a self-organizing network is proposed and analyzed. The criterion is based on a utility measure. When it is used in the context of the growing neural gas model to guide deletions of units, the resulting method is able to closely track non-stationary distributions. Slow changes of the distribution are handled by adaptation of existing units. Rapid changes are handled by removal of “useless” neurons and subsequent insertions of new units in other places. Additionally, the utility measure can be used to prune existing networks to a specified size with near-minimal increase of quantization error.

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.

Similar content being viewed by others

References

  1. H.-U. Bauer and Th. Villmann. Growing a hypercubical output space in a self-organizing feature map. TR-95-030, International Computer Science Institute, Berkeley, 1995.

    Google Scholar 

  2. B. Fritzke. Growing cell structures-a self-organizing network for unsupervised and supervised learning. Neural Networks, 7(9):1441–1460, 1994.

    Article  Google Scholar 

  3. B. Fritzke. A growing neural gas network learns topologies. In G. Tesauro, D. S. Touretzky, and T. K. Leen, editors, Advances in Neural Information Processing Systems 7, pages 625–632. MIT Press, Cambridge MA, 1995.

    Google Scholar 

  4. B. Fritzke. Growing grid-a self-organizing network with constant neighborhood range and adaptation strength. Neural Processing Letters, 2(5):9–13, 1995.

    Article  Google Scholar 

  5. B. Fritzke. The LBG-U method for vector quantization-an improvement over LBG inspired from neural networks. Neural Processing Letters, 5(1):35–45, 1997.

    Article  Google Scholar 

  6. T. Kohonen. Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43:59–69, 1982.

    Article  MATH  MathSciNet  Google Scholar 

  7. T. M. Martinetz. Competitive Hebbian learning rule forms perfectly topology preserving maps. In ICANN’93: International Conference on Artificial Neural Networks, pages 427–434, Amsterdam, 1993. Springer.

    Google Scholar 

  8. T. M. Martinetz, S. G. Berkovich, and K. J. Schulten. Neural-gas network for vector quantization and its application to time-series prediction. IEEE Transactions on Neural Networks, 4(4):558–569, 1993.

    Article  Google Scholar 

  9. RMS91. H. J. Ritter, T. M. Martinetz, and K. J. Schulten. Neuronale Netze. Addison-Wesley, München, 1991. 2. Auflage.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Neural Computation Group, Dresden University of Technology, Institute for Artificial Intelligence, Dresden

    Bernd Fritzke

Authors
  1. Bernd Fritzke
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institut für Informatik III, Universität Bonn, Römerstraße 164, D-53117, Bonn, Germany

    Wolfram Burgard  & Armin B. Cremers  & 

  2. GMD-Forschungszentrum Informationstechnik GmbH, Schloß Birlinghoven, D-53754, Sankt Augustin, Germany

    Thomas Cristaller

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fritzke, B. (1999). Be Busy and Unique — or Be History—The Utility Criterion for Removing Units in Self-Organizing Networks. In: Burgard, W., Cremers, A.B., Cristaller, T. (eds) KI-99: Advances in Artificial Intelligence. KI 1999. Lecture Notes in Computer Science(), vol 1701. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48238-5_17

Download citation

  • DOI: https://doi.org/10.1007/3-540-48238-5_17

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-66495-6

  • Online ISBN: 978-3-540-48238-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation