The Interconnectability Of Neuro-Optic Processors

T. Jannson; H. M. Stoll; C. Karaguleff

doi:10.1117/12.976258

23 March 1986 The Interconnectability Of Neuro-Optic Processors

T. Jannson, H. M. Stoll, C. Karaguleff

Proceedings Volume 0698, Real-Time Signal Processing IX; (1986) https://doi.org/10.1117/12.976258
Event: 30th Annual Technical Symposium, 1986, San Diego, United States

Abstract

The inherent parallelism, great processing speed, and massive interconnectability of optical systems have made the latter natural candidates for realizing various neural net models of associative memory, feature extraction, novelty filtering and problem optimization. Moreover, through the use of nonlinear thresholding and feedback techniques, such systems (hereafter referred to as neuro-optic processors or NOPs) appear to achieve the degree of operational accuracy long sought after in analog optical processor systems. Key elements of a typical NOP architecture include an optical interconnect network, an array of nonlinear optical processing elements, and a suitable means for providing optical feedback. In this paper we address ourselves to the optical interconnect network. Specifically we present practical design and information storage capacity analyses of the covariance matrix operator, = Emni=ilvm, >< Vmd, which characterizes this interconnect network. Here > is Hilbert-space object (state) vector in discrete or continuous 2D configuration space (in Dirac notation) and M represents the extent of NOP exposure to a particular object domain (within the context of pattern recognition, for example, M is the number of elements in a training pattern set). Central to our analyses is a discussion of the holographic technique which may be used to make R in hardware form.

Citation Download Citation

T. Jannson, H. M. Stoll, and C. Karaguleff "The Interconnectability Of Neuro-Optic Processors", Proc. SPIE 0698, Real-Time Signal Processing IX, (23 March 1986); https://doi.org/10.1117/12.976258

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