An unsupervised training connectionist network with lateral inhibition

  • Levente Kocsis
  • Nicolae B. Szirbik
3 Machine Learning Learning Advances in Neural Networks
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1416)


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.


Lateral Inhibition Input Pattern Training Base Pattern Separation Training Epoch 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [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. [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. [3]
    Hertz, J., Krogh, A., Palmer, R.G., “Introduction to the Theory of Neural Computation”, Addison-Wesley, Reading, MA, 1991.Google Scholar
  4. [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. [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. [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. [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. [8]
    Torioka, T., “Pattern separability in random neural net with inhibitory connections”, Biological Cybernetics, 34, pp 53–62, 1979.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Levente Kocsis
    • 1
  • Nicolae B. Szirbik
    • 1
  1. 1.Department of Computer ScienceTechnical University of TimisoaraTimisoaraRomania

Personalised recommendations