Skip to main content
SpringerLink
Log in

An unsupervised training connectionist network with lateral inhibition

  • 3 Machine Learning
  • Conference paper
  • First Online:
Tasks and Methods in Applied Artificial Intelligence (IEA/AIE 1998)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1416))

  • 1675 Accesses

Abstract

A new architecture for unsupervised learning is proposed. The topology, activation rules, and training algorithm are presented and a specific training base is used to prove the advantages of this type of network. The training patterns are from chess playing, but there are several other applications for this kind of system, and a specific one is proposed without going into details. Experimental results emphasize the performances of the network training.

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. Gobet, F., Jansen, P., “Towards a chess program based on a model of human memory”, in “Advances in Computer Chess 7”, (eds. H.J. van den Herik, I.S. Herschberg, J.E. Uiterwijk), University of Limburg Press, Maastricht, Belgium, 1994.

    Google Scholar 

  2. Gobet, F., Simon, H.A., “Templates in Chess Memory: A Mechanists for Recalling Several Boards”, Cognitive Psychology, 31, pp 1–40, 1996.

    Google Scholar 

  3. Hertz, J., Krogh, A., Palmer, R.G., “Introduction to the Theory of Neural Computation”, Addison-Wesley, Reading, MA, 1991.

    Google Scholar 

  4. Kung, H.T., Diamantuas, C.I., “A neural network learning algorithm for adaptive principal component extraction (APEX).”, International Conference on Acoustics, Speech, and Signal Processing, 2, pp 861–864, Albuquerque, NM 1990.

    Google Scholar 

  5. O'Reilly, R.C., McClelland, J.L., “Hippocampal Conjunctive Encoding, Storage and Recall: Avoiding a Tradeoff”, TR-PDP-CNS-94-4, Carnegie Mellon University, Pittsburgh, PA, 1994.

    Google Scholar 

  6. Pearlmutter, B.A., “An Investigation of the Gradient Descent Process in Neural Networks”, TR-CS-96-114, Carnegie Mellon University, Pittsburgh, PA, 1996.

    Google Scholar 

  7. Szirbik, N.B., “Towards a Model of Multi-Agent Connectionist Hybrid Systems”, Proceedings of ANNES'95, IEEE Computer. Soc. Press, Los Alamitos, CA, pp 273–276, 1995.

    Google Scholar 

  8. Torioka, T., “Pattern separability in random neural net with inhibitory connections”, Biological Cybernetics, 34, pp 53–62, 1979.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Technical University of Timisoara, Bd. V. Parvan nr.2, 1900, Timisoara, Romania

    Levente Kocsis & Nicolae B. Szirbik

Authors
  1. Levente Kocsis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nicolae B. Szirbik
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Angel Pasqual del Pobil José Mira Moonis Ali

Rights and permissions

Reprints and permissions

Copyright information

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kocsis, L., Szirbik, N.B. (1998). An unsupervised training connectionist network with lateral inhibition. In: Pasqual del Pobil, A., Mira, J., Ali, M. (eds) Tasks and Methods in Applied Artificial Intelligence. IEA/AIE 1998. Lecture Notes in Computer Science, vol 1416. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64574-8_446

Download citation

  • DOI: https://doi.org/10.1007/3-540-64574-8_446

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-64574-0

  • Online ISBN: 978-3-540-69350-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation