Photorefractive optical neural network

Bernard H. Soffer; Yuri Owechko; Gilmore J. Dunning

doi:10.1117/12.22274

1 July 1990 Photorefractive optical neural network

Bernard H. Soffer, Yuri Owechko, Gilmore J. Dunning

Proceedings Volume 1319, Optics in Complex Systems; (1990) https://doi.org/10.1117/12.22274
Event: 15th International Optics in Complex Systems, 1990, Garmisch, Germany

Abstract

This paper discusses holographic neumi netwrk architectures in which the connection weights between neurons are implemented as gratings in a photorefrtive crystal. In particular, it will discuss the self-pumped optical neural network (SPONN), which is a fineed optical architecture which features massive parallelism and a much greater degree of interconnectivity than bus-oriented or hypercube electronic architectures.Connecüons between neurons are implemented as sets of angularly and spatially multiplexed volume phase gratings. SPONN is potentially capable of implementing neural networks consisting of 1O1O6 neurons with 109.1010 interconnections. The mapping of neural network models onto the architecture occurs naturally without the need for multiplexing neurons or dealing with the contention, muting, and communication bottleneck problems of electronic parallel computers. This simplifies the programming of the optical system.

Citation Download Citation

Bernard H. Soffer, Yuri Owechko, and Gilmore J. Dunning "Photorefractive optical neural network", Proc. SPIE 1319, Optics in Complex Systems, (1 July 1990); https://doi.org/10.1117/12.22274

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available