Share Email Print

Proceedings Paper

Three Layers Of Vector Outer Product Neural Networks For Optical Pattern Recognition
Author(s): Harold Szu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A single homogeneous layer of neural network is reviewed. For optical computing, a vector outer product model of neural network is fully explored and is characterized to be quasi-linear (QL). The relationships among the hetero-associative memory [AM], the ill-posed inverse association (solved by annealing algorithm Boltzmann machine (BM)), and the symmetric interconnect [T] of Hopfield's model E(N) are found by applying Wiener's criterion to the output feature f and setting [EQUATION].

Paper Details

Date Published: 13 February 1986
PDF: 19 pages
Proc. SPIE 0634, Optical and Hybrid Computing, (13 February 1986); doi: 10.1117/12.964021
Show Author Affiliations
Harold Szu, Naval Research Laboratory (United States)

Published in SPIE Proceedings Vol. 0634:
Optical and Hybrid Computing
Harold H. Szu, Editor(s)

© SPIE. Terms of Use
Back to Top