Share Email Print
cover

Proceedings Paper

Optical auto- and heteroassociative memory based on a high-order neural network
Author(s): Boris S. Kiselyov; Nickolay Yu Kulakov; Andrei L. Mikaelian; Vladimir A. Shkitin
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The high-order associative memory model is considered. Its optical implementation for bipolar vectors is proposed. A bit weighting method increasing the efficiency of the recognition of high-correlated patterns with the model order being decreased is proposed. Spatio-temporal and hetero-associative memory systems are considered. Numerical simulation results are given.

Paper Details

Date Published: 1 November 1991
PDF: 12 pages
Proc. SPIE 1621, Optical Memory and Neural Networks, (1 November 1991); doi: 10.1117/12.50440
Show Author Affiliations
Boris S. Kiselyov, Scientific Council for Cybernetics (Russia)
Nickolay Yu Kulakov, Scientific Council for Cybernetics (Russia)
Andrei L. Mikaelian, Scientific Council for Cybernetics (Russia)
Vladimir A. Shkitin, Scientific Council for Cybernetics (Russia)


Published in SPIE Proceedings Vol. 1621:
Optical Memory and Neural Networks
Andrei L. Mikaelian, Editor(s)

© SPIE. Terms of Use
Back to Top