Emulating the dynamics for a class of laterally inhibited neural networks

Abstract This paper provides an input output description for a special class of laterally inhibited neural networks. The description allows us to predict which neurons will become active by using a simple algorithm that does not require numerical integration of the network's differential equations. This algorithm can be efficiently emulated on a VLSI bit array processor for moderately sized applications. As such devices are commercially available, we can realize moderately sized laterally inhibited neural networks with existing digital computing technologies.

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

[2]  Åke Björck,et al.  Numerical Methods , 1995, Handbook of Marine Craft Hydrodynamics and Motion Control.

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

[4]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[5]  S. Kung,et al.  VLSI Array processors , 1985, IEEE ASSP Magazine.

[6]  M. Hirsch.  The dynamical systems approach to differential equations , 1984 .

[7]  S. Grossberg.  Competition, Decision, and Consensus , 1978 .

[8]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[9]  R. May,et al.  Nonlinear Aspects of Competition Between Three Species , 1975 .

[10]  Stephen Grossberg,et al.  Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks , 1973 .

[11]  J. Cowan,et al.  Excitatory and inhibitory interactions in localized populations of model neurons. , 1972, Biophysical journal.

[12]  S. Smale.  On the differential equations of species in competition , 1976, Journal of mathematical biology.

[13]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[14]  Hal L. Smith.  Systems of ordinary differential equations which generate an order preserving flow. A survey of results , 1988 .

[16]  Shun-ichi Amari,et al.  Competitive and Cooperative Aspects in Dynamics of Neural Excitation and Self-Organization , 1982 .

[17]  J. Cowan,et al.  Large Scale Spatially Organized Activity in Neural Nets , 1980 .

[18]  Lee A. Segel,et al.  Mathematical models in molecular and cellular biology , 1982, The Mathematical Gazette.

[19]  M. Hirsch.  Systems of Differential Equations that are Competitive or Cooperative II: Convergence Almost Everywhere , 1985 .

[20]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .