An exactly solvable model for competitive networks
- 21 June 1989
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 22 (12) , 2047-2056
- https://doi.org/10.1088/0305-4470/22/12/010
Abstract
An energy function is proposed whose long-time dynamic behaviour is believed to resemble that of a realistic large competitive neural network. A simple model which gives rise to this energy function is described. The model is solved exactly for a finite number of patterns in the thermodynamic limit using mean-field theory. Simulations of this model are presented. The behaviour of large competitive networks is discussed.Keywords
This publication has 11 references indexed in Scilit:
- Statistical mechanics of neural networks near saturationPublished by Elsevier ,2004
- Self-organization in a perceptual networkComputer, 1988
- From basic network principles to neural architecture: emergence of orientation columns.Proceedings of the National Academy of Sciences, 1986
- From basic network principles to neural architecture: emergence of orientation-selective cells.Proceedings of the National Academy of Sciences, 1986
- From basic network principles to neural architecture: emergence of spatial-opponent cells.Proceedings of the National Academy of Sciences, 1986
- Spin-glass models of neural networksPhysical Review A, 1985
- Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectorsBiological Cybernetics, 1976
- Development of Specificity in the Cat Visual CortexJournal of Mathematical Biology, 1975
- Cognitron: A self-organizing multilayered neural networkBiological Cybernetics, 1975
- Self-organization of orientation sensitive cells in the striate cortexBiological Cybernetics, 1973