
Carsten Peterson
Expert

Optoelectronic implementation of multilayer neural networks in a single photorefractive crystal
Författare
Summary, in English
We present a novel, versatile optoelectronic neural network architecture for implementing supervised learning algorithms in photorefractive materials. The system is based on spatial multiplexing rather than the more commonly used angular multiplexing of the interconnect gratings. This simple, single-crystal architecture implements a variety of multilayer supervised learning algorithms including mean field theory, back-propagation, and Marr-Albus-Kanerva style algorithms. Extensive simulations show how beam depletion, rescattering, absorption, and decay effects of the crystal are compensated for by suitably modified supervised learning algorithms.
Avdelning/ar
- Computational Biology and Biological Physics
Publiceringsår
1990-04-01
Språk
Engelska
Sidor
359-368
Publikation/Tidskrift/Serie
Optical Engineering
Volym
29
Issue
4
Dokumenttyp
Artikel i tidskrift
Förlag
SPIE
Ämne
- Computer Science
Aktiv
Published
ISBN/ISSN/Övrigt
- ISSN: 0091-3286