Competitive Repetition-suppression (CoRe) Learning

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.

[1]  Nicolaos B. Karayiannis,et al.  Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques , 1997, IEEE Trans. Neural Networks.

[2]  Erkki Oja,et al.  Rival penalized competitive learning for clustering analysis, RBF net, and curve detection , 1993, IEEE Trans. Neural Networks.

[3]  E. Bienenstock,et al.  Theory for the development of neuron selectivity: orientation specificity and binocular interaction in visual cortex , 1982, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[4]  Misha Tsodyks,et al.  Neural networks and perceptual learning , 2004, Nature.

[5]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[6]  Robert M. French,et al.  Semi-distributed Representations and Catastrophic Forgetting in Connectionist Networks , 1992 .

[7]  Steven J. Nowlan,et al.  Soft competitive adaptation: neural network learning algorithms based on fitting statistical mixtures , 1991 .

[8]  Duane DeSieno,et al.  Adding a conscience to competitive learning , 1988, IEEE 1988 International Conference on Neural Networks.

[9]  J. Paetz,et al.  Feature selection for RBF networks , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[10]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[11]  L.N. de Castro,et al.  An evolutionary clustering technique with local search to design RBF neural network classifiers , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[12]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[13]  Joydeep Ghosh,et al.  Frequency-sensitive competitive learning for scalable balanced clustering on high-dimensional hyperspheres , 2004, IEEE Transactions on Neural Networks.

[14]  R. Desimone,et al.  Neural mechanisms for visual memory and their role in attention. , 1996, Proceedings of the National Academy of Sciences of the United States of America.