13 February 1986 Three Layers Of Vector Outer Product Neural Networks For Optical Pattern Recognition
Author Affiliations +
Proceedings Volume 0634, Optical and Hybrid Computing; (1986) https://doi.org/10.1117/12.964021
Event: Optical and Hybrid Computing, 1986, Leesburg, United States
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].
© (1986) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Harold Szu, "Three Layers Of Vector Outer Product Neural Networks For Optical Pattern Recognition", Proc. SPIE 0634, Optical and Hybrid Computing, (13 February 1986); doi: 10.1117/12.964021; https://doi.org/10.1117/12.964021
PROCEEDINGS
19 PAGES


SHARE
Back to Top