Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Nowlan, S.: Soft Competitive Adaptation: Neural Network Learning Algorithms based on Fitting Statistical Mixtures. Phd thesis, Carnegie-Mellon University, Pittsburg (1991)
DeSieno, D.: Adding conscience to competitive learning. In: IEEE Annu. Int. Conf. Neural Networks, pp. 1117–1124. IEEE Computer Society, Los Alamitos (1988)
Desimone, R.: Neural mechanisms for visual memory and their role in attention. Proceedings of Natl. Acad. Sci. USA 93, 13494–13499 (1996)
Poggio, T., Girosi, F.: Networks for approximation and learning. Proceedings of the IEEE 78, 1481–1497 (1990)
Tdodyks, M., Gilbert, C.: Neural networks and perceptual priming. Nature 7010(431), 775–781 (2004)
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)
French, R.M.: Semi-distributed representations and catastrophic forgetting in connectionist networks. Connection Science 4, 365–377 (1992)
Rumelhart, D., Zipser, D.: Competitive learning. Cognitive Science 9, 75–112 (1985)
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)
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)
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)
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)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugenics 7(2), 179–188 (1936)
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)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bacciu, D., Starita, A. (2006). Competitive Repetition-suppression (CoRe) Learning. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds) Artificial Neural Networks – ICANN 2006. ICANN 2006. Lecture Notes in Computer Science, vol 4131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11840817_14
Download citation
DOI: https://doi.org/10.1007/11840817_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-38625-4
Online ISBN: 978-3-540-38627-8
eBook Packages: Computer ScienceComputer Science (R0)