Share Email Print
cover

Proceedings Paper

Optical neural network with reconfigurable holographic interconnection
Author(s): Andrew G. Kirk; G. D. Kendall; Hasan T. Imam; Trevor J. Hall
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

A high-performance bipolar analogue optical neural network with flexible architecture has been designed. This is achieved by the use of an all-optical two-dimensional global interconnection system that uses holographic multiple imaging. The weight matrix and input planes of the neural network are determined by spatial light modulators (SLM). This facilitates learning in situ with direct learning techniques proposed. Simulated results from the optical analogue neural network are presented using image processing primitives as a demonstrator.

Paper Details

Date Published: 1 November 1991
PDF: 8 pages
Proc. SPIE 1621, Optical Memory and Neural Networks, (1 November 1991); doi: 10.1117/12.50439
Show Author Affiliations
Andrew G. Kirk, King's College London (United Kingdom)
G. D. Kendall, King's College London (United Kingdom)
Hasan T. Imam, King's College London (United Kingdom)
Trevor J. Hall, King's College London (United Kingdom)


Published in SPIE Proceedings Vol. 1621:
Optical Memory and Neural Networks

© SPIE. Terms of Use
Back to Top