Share Email Print

Proceedings Paper

Liquid-crystal television optical neural network: architecture, design, and models
Author(s): Francis T. S. Yu
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

An adaptive optical neural network (ONN) using inexpensive pocket-size liquid crystal televisions (LCTVs) and containing 8 X 8 equals 64 neurons was constructed by a group of graduate students in the Electro-Optics Laboratory at The Pennsylvania State University. By the limited resolution of the LCTV, the current optical architecture can be easily extended to 16 X 20 equals 320 neurons. The major advantages of this LCTV architecture as compared with other reported ONNs are low cost and the flexibility to operate. To test the performance, several neural network models are implemented, in which are interpattern association, hetero- association, and unsupervised learning algorithm. The system design considerations and experimental demonstrations of the neural network models are given.

Paper Details

Date Published: 1 June 1991
PDF: 17 pages
Proc. SPIE 1455, Liquid-Crystal Devices and Materials, (1 June 1991); doi: 10.1117/12.44688
Show Author Affiliations
Francis T. S. Yu, The Pennsylvania State Univ. (United States)

Published in SPIE Proceedings Vol. 1455:
Liquid-Crystal Devices and Materials
Paul S. Drzaic; Uzi Efron, Editor(s)

© SPIE. Terms of Use
Back to Top