Paper
9 November 1993 Holographic neurocomputer for backpropagation based on cascaded-grating holography
Yuri Owechko, Bernard H. Soffer
Author Affiliations +
Abstract
We describe recent results for implementation of the backpropagation neural network on an experimental optical neurocomputer developed under ARPA sponsorship. Weights are stored holographically in a photorefractive crystal using a recording method which eliminates crosstalk due to Bragg degeneracy and permits full utilization of the input and output. Experimental results are discussed for handwritten digit recognition.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yuri Owechko and Bernard H. Soffer "Holographic neurocomputer for backpropagation based on cascaded-grating holography", Proc. SPIE 2026, Photonics for Processors, Neural Networks, and Memories, (9 November 1993); https://doi.org/10.1117/12.163595
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neural networks

Neurons

Holography

Computer generated holography

Holograms

Spatial light modulators

Fractal analysis

RELATED CONTENT

Multilayer optical neural networks
Proceedings of SPIE (February 02 1993)
Adaptive holographic implementation of a neural network
Proceedings of SPIE (July 01 1990)
Holographic Routing Network For Parallel Processing Machines
Proceedings of SPIE (October 26 1989)

Back to Top