Share Email Print
cover

Optical Engineering

Design of fiber optic adaline neural networks
Author(s): Anjan K. Ghosh; Jim Trepka
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Based on possible optoelectronic realization of adaptive filters and equalizers using fiber optic tapped delay lines and spatial light modulators we describe the design of a single-layer fiber optic Adaline neural network that can be used as a bit pattern classifier. In our design, we employ as few electronic devices as possible and use optical computation to utilize the advantages of optics in processing speed, parallelism, and interconnection. The described new optical neural network design is for optical processing of guided light wave signals, not electronic signals. We analyze the convergence or learning characteristics of the optoelectronic Adaline in the presence of errors in the hardware. We show that with such an optoelectronic Adaline it is possible to detect a desired code word/token/header with good accuracy.

Paper Details

Date Published: 1 March 1997
PDF: 6 pages
Opt. Eng. 36(3) doi: 10.1117/1.601138
Published in: Optical Engineering Volume 36, Issue 3
Show Author Affiliations
Anjan K. Ghosh, Univ. of Iowa (India)
Jim Trepka, Univ. of Iowa (United States)


© SPIE. Terms of Use
Back to Top