Share Email Print
cover

Proceedings Paper

Holographic neurocomputer utilizing laser diode light source
Author(s): Yuri Owechko; Bernard H. Soffer
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We describe a laser diode-based optoelectronic implementation of artificial neural networks which utilizes real-time holography in photorefractive crystals. The use of a laser diode light source reduces the system size and power requirements. The holographic material is rhodium- doped BaTiO3 which has enhanced sensitivity at the laser-diode wavelength of 830 nm. A balanced coherent-detection method is used to represent bipolar optical neurons and weights. In addition, by distributing each neuron weight among a set of spatially and angularly distributed gratings using beam fanning, Bragg degeneracy and its associated inter-neuron optical crosstalk is virtually eliminated. The structure of the neural network is programmable and we have implemented a variety of neural networks including backpropagation and Kohonen-style self-organizing maps with up to 10,000 neurons and performance of up to 108 weights processed per second during learning and readout. We also discuss weight decay in photorefractive materials, specifically its relative effects in the neural network and data storage domains.

Paper Details

Date Published: 28 August 1995
PDF: 8 pages
Proc. SPIE 2565, Optical Implementation of Information Processing, (28 August 1995); doi: 10.1117/12.217654
Show Author Affiliations
Yuri Owechko, Hughes Research Labs. (United States)
Bernard H. Soffer, Hughes Research Labs. (United States)


Published in SPIE Proceedings Vol. 2565:
Optical Implementation of Information Processing
Bahram Javidi; Joseph L. Horner, Editor(s)

© SPIE. Terms of Use
Back to Top