A Polarization Based Optical Connectionist Machine

Mike Kranzdorf; Kristina M. Johnson; Lise Cotter; Lin Zhang; B.Jack Bigner

doi:10.1117/12.947931

8 February 1988 A Polarization Based Optical Connectionist Machine

Mike Kranzdorf, Kristina M. Johnson, Lise Cotter, Lin Zhang, B.Jack Bigner

Proceedings Volume 0963, Optical Computing '88; (1988) https://doi.org/10.1117/12.947931
Event: Optical Computing '88, 1988, Toulon, France

Abstract

Simulations of massively parallel connectionist systems are very time consuming on serial computers . Vector-matrix multiplications, which are a common calculation of many popular connectionist architectures, require 0(n²) operations on serial machines. A simple optical architecture can perform this calculation in nearly constant time, neglecting the machine loading time. The parallelism in such optical designs makes them attractive for implementation of connectionist models. We have demonstrated an optoelectronic connectionist module with modifiable inputs and weight matrices that performs associative memory operations. Low cost commercial liquid crystal television sets are used to encode unit activities as intensity of linearly polarized light, and signed multiplication as rotation of this light. Integrated computer control will allow the extension to many connectionist models.

Citation Download Citation

Mike Kranzdorf, Kristina M. Johnson, Lise Cotter, Lin Zhang, and B.Jack Bigner "A Polarization Based Optical Connectionist Machine", Proc. SPIE 0963, Optical Computing '88, (8 February 1988); https://doi.org/10.1117/12.947931

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