Share Email Print
cover

Proceedings Paper

Fast optoelectronic neurocomputer for character recognition
Author(s): Lin Zhang; Michael G. Robinson; Kristina M. Johnson
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Optical implementations of neural networks utilize the inherent parallelism of optics to form the large number of interconnections required by neural networks. By carrying out computations in parallel, the processing speed of such systems can be substantial, despite the relatively slow response times of the optical devices. In this paper, a single-layer neural network is presented, which uses ferroelectric liquid crystal (FLC) spatial light modulators (SLM) to represent input patterns and weighted interconnections. The learning example for the network is handwritten character recognition. The experiment shows that this network successfully recognizes 58 of the handwritten patterns from the training set, when the synaptic weights have five grey levels and a dynamic range from -1 to +1. Computer simulations of networks indicate that by increasing the grey levels to eleven, and the dynamic range from -12.5 to +12.5, this net easily learns to recognize all the handwritten patterns in the training set. It also correctly recognizes 60 of the test patterns.

Paper Details

Date Published: 1 August 1991
PDF: 5 pages
Proc. SPIE 1469, Applications of Artificial Neural Networks II, (1 August 1991); doi: 10.1117/12.45024
Show Author Affiliations
Lin Zhang, Univ. of Colorado/Boulder (United States)
Michael G. Robinson, Univ. of Colorado/Boulder (United States)
Kristina M. Johnson, Univ. of Colorado/Boulder (United States)


Published in SPIE Proceedings Vol. 1469:
Applications of Artificial Neural Networks II
Steven K. Rogers, Editor(s)

© SPIE. Terms of Use
Back to Top