Share Email Print

Proceedings Paper

Modification Of The Hopfield Model And Its Optical Implementation For Correlated Images
Author(s): Soo-Young Lee; Ju-Seog Jang; Jin-Soo Park; Sang-Yung Shin; Chang-Sup Shim
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

Introducing and optimizing bit-significance to the Hopfield model, ten highly correlated binary images, i.e., numbers "0" to "9", are successfully stored and retrieved in a 6x8 node system. Unlike many other neural networks models, this model has stronger error correction capability for correlated images such as "6", "8", "3", and "9". The bit-significance optimization is regarded as an adaptive learning process based on least-mean-square error algorithm, and may be implemented with another neural nets optimizer. A design for electro-optic implementation including the adaptive optimization networks is also introduced.

Paper Details

Date Published: 8 February 1988
PDF: 8 pages
Proc. SPIE 0963, Optical Computing '88, (8 February 1988); doi: 10.1117/12.947930
Show Author Affiliations
Soo-Young Lee, Korea Advanced Institute of Science and Technology (Korea)
Ju-Seog Jang, Korea Advanced Institute of Science and Technology (Korea)
Jin-Soo Park, Korea Advanced Institute of Science and Technology (Korea)
Sang-Yung Shin, Korea Advanced Institute of Science and Technology (Korea)
Chang-Sup Shim, Korea Electronic and Telecommunication Research Institute (Korea)

Published in SPIE Proceedings Vol. 0963:
Optical Computing '88
Pierre H. Chavel; Joseph W. Goodman; Gerard Roblin, Editor(s)

© SPIE. Terms of Use
Back to Top