Share Email Print
cover

Proceedings Paper

Neural-like holographic information system for processing of optical signals
Author(s): Yuri N. Kulchin; Oleg B. Vitric; Igor V. Denisov; Oleg T. Kamenev; Oleg V. Kirichenko
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The main advantages of a neural networks are the flexibility of architecture and ability to training. It allows to perform data processing even when the processing procedure can not be present by the known function. The neural networks based on optical elements allow real time operation rather than electronic neural networks. We offered system, based on neural networks, capabling to solve a broad class of heterogeneous problems and adapting to input information flow. The system are based on neural networks of two types: (1) a single-pass network of perceptron type and (2) recognize network of Hopfield network type. The neural network of the type (1) is realized by holographic scheme and experimental checked when processing the signals fiber- optic measuring network.

Paper Details

Date Published: 1 April 1998
PDF: 3 pages
Proc. SPIE 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks, (1 April 1998); doi: 10.1117/12.304968
Show Author Affiliations
Yuri N. Kulchin, Far-Eastern State Technical Univ. (Russia)
Oleg B. Vitric, Far-Eastern State Technical Univ. (Russia)
Igor V. Denisov, Far-Eastern State Marine Academy (Russia)
Oleg T. Kamenev, Far-Eastern State Technical Univ. (Russia)
Oleg V. Kirichenko, Far-Eastern State Technical Univ. (Russia)


Published in SPIE Proceedings Vol. 3402:
Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks
Andrei L. Mikaelian, Editor(s)

© SPIE. Terms of Use
Back to Top