Learning in a competitive network

Abstract We consider the abilities of a recently published neural network model to recognize and classify arbitrary patterns. We introduce a learning scheme based on Hebb's rule which allows the system's neuronal cells to specialize on different patterns during learning. The rule which was originally introduced by Kohonen is appropriately modified and applied to the competitive network under study. A variant of the learning dynamics is then derived from an energy functional characterizing the specialization state of the network. Simulations are presented to demonstrate the specialization process for different pattern distributions.

[1]  R Linsker,et al.  From basic network principles to neural architecture: emergence of orientation-selective cells. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[2]  D. Hubel,et al.  EFFECTS OF VISUAL DEPRIVATION ON MORPHOLOGY AND PHYSIOLOGY OF CELLS IN THE CATS LATERAL GENICULATE BODY. , 1963, Journal of neurophysiology.

[3]  Armin Fuchs,et al.  Nonequilibrium phase transitions in pattern recognition and associative memory. Numerical results , 1988 .

[4]  Hermann Haken,et al.  Nonequilibrium phase transitions in pattern recognition and associative memory , 1988 .

[5]  R Linsker,et al.  From basic network principles to neural architecture: emergence of spatial-opponent cells. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Stephen Grossberg,et al.  Studies of mind and brain , 1982 .

[7]  T. Kohonen.  Self-Organized Formation of Correct Feature Maps , 1982 .

[8]  D. O. Hebb,et al.  The organization of behavior , 1988 .

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

[10]  E. Oja.  Simplified neuron model as a principal component analyzer , 1982, Journal of mathematical biology.

[11]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[12]  Stephen Grossberg,et al.  Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[13]  Roman Bek,et al.  Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[14]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[15]  Hermann Haken.  Pattern Formation and Pattern Recognition — An Attempt at a Synthesis , 1979 .

[16]  H. Haken,et al.  Synergetic Computers for Pattern Recognition and Associative Memory , 1987 .

[17]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.