12 July 1993 Renewal method of weight matrix in optical neural network
Author Affiliations +
Proceedings Volume 1806, Optical Computing; (1993) https://doi.org/10.1117/12.147840
Event: Topical Meeting on Optical Computing, 1992, Minsk, Belarus
Abstract
We proposed a new renewal method of the weights to realize a back propagation learning algorithm with a large number of iteration times in an optical neural network. The main purpose of this method is to use the limited dynamic range of an optical device widely. Since some weights displaying on the device are quickly saturated in the conventional method, the learning is not completed in many cases. The new technique can suppress saturation of the weights so that learning is completed. The computer simulation and the optical experiment are presented.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ichiro Tohyama, Ichiro Tohyama, Yoshio Hayasaki, Yoshio Hayasaki, Toyohiko Yatagai, Toyohiko Yatagai, Masahiko Mori, Masahiko Mori, Satoshi Ishihara, Satoshi Ishihara, } "Renewal method of weight matrix in optical neural network", Proc. SPIE 1806, Optical Computing, (12 July 1993); doi: 10.1117/12.147840; https://doi.org/10.1117/12.147840
PROCEEDINGS
8 PAGES


SHARE
Back to Top