Share Email Print
cover

Proceedings Paper

Designing and simulation of optoelectronic neural networks with the help of equivalence models and multivalued logics
Author(s): Vladimir G. Krasilenko; Anatoly K. Bogukhvalsky; Andrey T. Magas
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The theory and equivalental models of neural networks based on equivalence operation of continuous and multivalued neural logic are considered. Their connection with metric of metric-address spaces are shown. Normalized equivalences of vectors with multilevel components are determined. Equivalental models for simple network with weighted correlation coefficients, for network with adapted weighing and double weighing are suggested. It is shown, that the network model with double weighing being most generalized can also conduct the recalculation process of networks to two-step algorithms without calculation of connections matrix. Equivalent models require calculations based on vector-matrix procedures with equivalence operation and can be realized on vector-matrix calculations based on vector- matrix procedures with equivalence operation and can be realized on vector-matrix equivalentors with space and time integration. The apparatus implementations of models with productivity of 108 divided by 109 connections/sec and neuron number 256 and more are suggested.

Paper Details

Date Published: 11 November 1996
PDF: 12 pages
Proc. SPIE 2824, Adaptive Computing: Mathematical and Physical Methods for Complex Environments, (11 November 1996); doi: 10.1117/12.258126
Show Author Affiliations
Vladimir G. Krasilenko, Injector Collective Scientific-Industrial Venture (Ukraine)
Anatoly K. Bogukhvalsky, Injector Collective Scientific-Industrial Venture (Ukraine)
Andrey T. Magas, Injector Collective Scientific-Industrial Venture (Ukraine)


Published in SPIE Proceedings Vol. 2824:
Adaptive Computing: Mathematical and Physical Methods for Complex Environments
H. John Caulfield; Su-Shing Chen, Editor(s)

© SPIE. Terms of Use
Back to Top