Stimulated Photorefractive Optical Neural Networks
Abstract
This final report describes research in optical neural networks performed under DARPA sponsorship at Hughes Aircraft Company during the period 1989-1992. The objective of demonstrating a programmable optical computer for flexible implementation of multi-layer neural network models was successfully achieved. The advantages of optics for neural network implementations include large storage capacity, high connectivity, and massive parallelism which result in high computation rates. The optical neurocomputer developed on this program is based on a new type of holography, cascaded grating holography (CGH), in which the neural network weights are distributed among angularly- and spatially- multiplexed gratings generated by stimulated processes in photorefractive crystals. This approach reduces crosstalk and improves the utilization of the optical input device. Successfully implemented neural networks include the Perceptron, Bidirectional Associative Memory, and multi-layer backpropagation networks. Up to 104 neurons, 2xl0(7) weights, and processing rates of 2xl0(7) connection updates per second were achieved. Packaging concepts for future versions of the neurocomputer were also studied.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 15, 1992
- Accession Number
- ADA258825
Entities
People
- B. H. Soffer
- G. Dunning
- G. Nordin
- Y. Owechko
Organizations
- HRL Laboratories