Competitive Repetition-suppression (CoRe) Learning

  • Davide Bacciu
  • Antonina Starita
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4131)


The paper introduces Competitive Repetition-suppression (CoRe) learning, a novel paradigm inspired by a cortical mechanism of perceptual learning called repetition suppression. CoRe learning is an unsupervised, soft-competitive [1] model with conscience [2] that can be used for self-generating compact neural representations of the input stimuli. The key idea underlying the development of CoRe learning is to exploit the temporal distribution of neurons activations as a source of training information and to drive memory formation. As a case study, the paper reports the CoRe learning rules that have been derived for the unsupervised training of a Radial Basis Function network.


Input Pattern Perceptual Learning Radial Basis Function Network Input Stimulus Competitive Learning 
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.
    Nowlan, S.: Soft Competitive Adaptation: Neural Network Learning Algorithms based on Fitting Statistical Mixtures. Phd thesis, Carnegie-Mellon University, Pittsburg (1991)Google Scholar
  2. 2.
    DeSieno, D.: Adding conscience to competitive learning. In: IEEE Annu. Int. Conf. Neural Networks, pp. 1117–1124. IEEE Computer Society, Los Alamitos (1988)Google Scholar
  3. 3.
    Desimone, R.: Neural mechanisms for visual memory and their role in attention. Proceedings of Natl. Acad. Sci. USA 93, 13494–13499 (1996)CrossRefGoogle Scholar
  4. 4.
    Poggio, T., Girosi, F.: Networks for approximation and learning. Proceedings of the IEEE 78, 1481–1497 (1990)CrossRefGoogle Scholar
  5. 5.
    Tdodyks, M., Gilbert, C.: Neural networks and perceptual priming. Nature 7010(431), 775–781 (2004)CrossRefGoogle Scholar
  6. 6.
    Mozer, M.C., Mytkowicz, T., Zemel, R.S.: Achieving robust neural representations:an account of repetition suppression. Technical report, Computer Science Deparment, University of Colorado, Boulder (2004)Google Scholar
  7. 7.
    French, R.M.: Semi-distributed representations and catastrophic forgetting in connectionist networks. Connection Science 4, 365–377 (1992)CrossRefGoogle Scholar
  8. 8.
    Rumelhart, D., Zipser, D.: Competitive learning. Cognitive Science 9, 75–112 (1985)CrossRefGoogle Scholar
  9. 9.
    Xu, L., Krzyzak, A., Oja, E.: Rival penalized competitive learning for clustering analysis, rbf net, and curve detection. IEEE Transactions on Neural Networks 4(4), 636–649 (1993)CrossRefGoogle Scholar
  10. 10.
    Banerjee, A., Ghosh, J.: Frequency-sensitive competitive learning for scalable balanced clustering on high-dimensional hyperspheres. IEEE Transactions on Neural Networks 15, 702–719 (2004)CrossRefGoogle Scholar
  11. 11.
    Bienenstock, E.L., Cooper, L.N., Munro, P.W.: Theory for the development of neuron selectivity: orientation specificity and binocular interaction in visual cortex. Neurocomputing: foundations of research, 437–455 (1988)Google Scholar
  12. 12.
    Karayiannis, N.: Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques. IEEE Transactions on Neural Networks 8(6), 1492–1506 (1997)CrossRefGoogle Scholar
  13. 13.
    Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugenics 7(2), 179–188 (1936)Google Scholar
  14. 14.
    de Castro, L.N., Hruschka, E.R., Campello, R.J.G.B.: An evolutionary clustering technique with local search to design RBF neural network classifiers. In: Proceedings of the 2004 IEEE International Joint Conference on Neural Networks, vol. 3, pp. 2083–2088 (2004)Google Scholar
  15. 15.
    Paetz, J.: Feature selection for RBF networks. In: Proceedings of the 9th International Conference on Neural Information Processing (ICONIP 2002), vol. 2, pp. 986–990 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Davide Bacciu
    • 1
    • 2
  • Antonina Starita
    • 2
  1. 1.IMT Lucca School for Advanced StudiesLuccaItaly
  2. 2.Dipartimento d’InformaticaUniversità degli Studi di PisaPisaItaly

Personalised recommendations