Share Email Print
cover

Proceedings Paper

Image recognition by means of two-layer holographic neural network
Author(s): Victor I. Kozik; Oleg I. Potaturkin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A hybrid optical-electronic system for pattern recognition based on a neural network model is under discussion. A structure of two-layered holographic neural network is proposed. In order to improve the iteration process an auxiliary sublayer with local connections is added to the first layer. A new class of optical high-performance processors -- intensity-linear holographic correlators to provide global connections in both layers of the neural network is proposed and discussed.

Paper Details

Date Published: 7 December 1994
PDF: 7 pages
Proc. SPIE 2430, Optical Memory & Neural Networks '94: Optical Neural Networks, (7 December 1994); doi: 10.1117/12.195607
Show Author Affiliations
Victor I. Kozik, Institute of Automation and Electrometry (Russia)
Oleg I. Potaturkin, Institute of Automation and Electrometry (Russia)


Published in SPIE Proceedings Vol. 2430:
Optical Memory & Neural Networks '94: Optical Neural Networks
Andrei L. Mikaelian, Editor(s)

© SPIE. Terms of Use
Back to Top