Share Email Print
cover

Proceedings Paper

Optical implementation of winner-take-all models of neural networks
Author(s): E. F. Kobzev; Mikhail A. Vorontsov
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The so called WTA ( " winner take all" ) model appears to be one of the most interesting models of artificial neural networks. '' In networks of this kind only one single neuron specified by maximum (or minimum) initial activity becomes active as a result of cooperative transient process. In this work the optical implementations of WTA neural network are presented. The example of WTA neural network demonstrates that due to the existence of strong NL competition the problem of global extremum search can actually be solved. It should be mentioned that this problem seems to be quite complicated for digital computers. It is worth adding that these neural networks have multiple applications.

Paper Details

Date Published: 1 April 1991
PDF: 10 pages
Proc. SPIE 1402, USSR-CSFR Joint Seminar on Nonlinear Optics in Control, Diagnostics, and Modeling of Biophysical Processes, (1 April 1991); doi: 10.1117/12.47500
Show Author Affiliations
E. F. Kobzev, Moscow State Univ. (Russia)
Mikhail A. Vorontsov, Moscow State Univ. (Russia)


Published in SPIE Proceedings Vol. 1402:
USSR-CSFR Joint Seminar on Nonlinear Optics in Control, Diagnostics, and Modeling of Biophysical Processes

© SPIE. Terms of Use
Back to Top