NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Optoelectronic analogs of self-programming neural nets - Architecture and methodologies for implementing fast stochastic learning by simulated annealingSelf-organization and learning is a distinctive feature of neural nets and processors that sets them apart from conventional approaches to signal processing. It leads to self-programmability which alleviates the problem of programming complexity in artificial neural nets. In this paper architectures for partitioning an optoelectronic analog of a neural net into distinct layers with prescribed interconnectivity pattern to enable stochastic learning by simulated annealing in the context of a Boltzmann machine are presented. Stochastic learning is of interest because of its relevance to the role of noise in biological neural nets. Practical considerations and methodologies for appreciably accelerating stochastic learning in such a multilayered net are described. These include the use of parallel optical computing of the global energy of the net, the use of fast nonvolatile programmable spatial light modulators to realize fast plasticity, optical generation of random number arrays, and an adaptive noisy thresholding scheme that also makes stochastic learning more biologically plausible. The findings reported predict optoelectronic chips that can be used in the realization of optical learning machines.
Document ID
19880035619
Acquisition Source
Legacy CDMS
Document Type
Reprint (Version printed in journal)
Authors
Farhat, Nabil H.
(Pennsylvania, University Philadelphia, United States)
Date Acquired
August 13, 2013
Publication Date
December 1, 1987
Publication Information
Publication: Applied Optics
Volume: 26
ISSN: 0003-6935
Subject Category
Cybernetics
Accession Number
88A22846
Distribution Limits
Public
Copyright
Other

Available Downloads

There are no available downloads for this record.
No Preview Available