Share Email Print

Proceedings Paper

Optoelectronic implementation of multilayer perceptron and Hopfield neural networks
Author(s): Andrzej W. Domanski; Mikolaj K. Olszewski; Tomasz R. Wolinski
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper we present an optoelectronic implementation of two networks based on multilayer perceptron and the Hopfield neural network. We propose two different methods to solve a problem of lack of negative optical signals that are necessary for connections between layers of perceptron as well as within the Hopfield network structure. The first method applied for construction of multilayer perceptron was based on division of signals into two channels and next to use both of them independently as positive and negative signals. The second one, applied for implementation of the Hopfield model, was based on adding of constant value for elements of matrix weight. Both methods of compensation of lack negative optical signals were tested experimentally as optoelectronic models of multilayer perceptron and Hopfield neural network. Special configurations of optical fiber cables and liquid crystal multicell plates were used. In conclusion, possible applications of the optoelectronic neural networks are briefly discussed.

Paper Details

Date Published: 2 November 2004
PDF: 7 pages
Proc. SPIE 5558, Applications of Digital Image Processing XXVII, (2 November 2004); doi: 10.1117/12.564613
Show Author Affiliations
Andrzej W. Domanski, Warsaw Univ. of Technology (Poland)
Mikolaj K. Olszewski, Warsaw Univ. of Technology (Poland)
Tomasz R. Wolinski, Warsaw Univ. of Technology (Poland)

Published in SPIE Proceedings Vol. 5558:
Applications of Digital Image Processing XXVII
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top