Share Email Print

Proceedings Paper

The Interconnectability Of Neuro-Optic Processors
Author(s): T. Jannson; H. M. Stoll; C. Karaguleff
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 23 March 1986
PDF: 13 pages
Proc. SPIE 0698, Real-Time Signal Processing IX, (23 March 1986); doi: 10.1117/12.976258
Show Author Affiliations
T. Jannson, Northrop Research and Technology Center (United States)
H. M. Stoll, Northrop Research and Technology Center (United States)
C. Karaguleff, Northrop Research and Technology Center (United States)

Published in SPIE Proceedings Vol. 0698:
Real-Time Signal Processing IX
William J. Miceli, Editor(s)

© SPIE. Terms of Use
Back to Top