Share Email Print

Proceedings Paper

An Optoelectronic Neural Network
Author(s): Mark A. A. Neil; Ian H. White; John E. Carroll
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We describe and present results of an optoelectronic neural network processing system. The system uses an algorithm based on the Hebbian learning rule to memorise a set of associated vector pairs. Recall occurs by the processing of the input vector with these stored associations in an incoherent optical vector multiplier using optical polarisation rotating liquid crystal spatial light modulators to store the vectors and an optical polarisation shadow casting technique to perform multiplications. Results are detected on a photodiode array and thresholded electronically by a controlling microcomputer. The processor is shown to work in autoassociative and heteroassociative modes with up to 10 stored memory vectors of length 64 (equivalent to 64 neurons) and a cycle time of 50ms. We discuss the limiting factors at work in this system, how they affect its scalability and the general applicability of its principles to other systems.

Paper Details

Date Published: 5 February 1990
PDF: 9 pages
Proc. SPIE 1151, Optical Information Processing Systems and Architectures, (5 February 1990); doi: 10.1117/12.962241
Show Author Affiliations
Mark A. A. Neil, Cambridge University (United Kingdom)
Ian H. White, Cambridge University (United Kingdom)
John E. Carroll, Cambridge University (United Kingdom)

Published in SPIE Proceedings Vol. 1151:
Optical Information Processing Systems and Architectures
Bahram Javidi, Editor(s)

© SPIE. Terms of Use
Back to Top