Share Email Print

Proceedings Paper

Projection Method Formulations Of Perceptron And Hopfield Associative Memory Neural Networks
Author(s): M. Ibrahim Sezan; Henry Stark; Shu-Jen Yeh
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Projection method formulations of the perceptron and Hopfield's associative content-addressable memory (ACAM) neural nets are presented. We show that the well-known single-layer perceptron learning algorithm can be formulated using the method of projections onto convex sets (POCS) and that its performance can be improved using this viewpoint. The operation of a modified, binary-valued Hopfield ACAM is shown to be equivalent to the method of generalized projections (GP). A direct extension of the binary-valued ACAM to the continuous-valued case lends itself to a POCS formu-lation.

Paper Details

Date Published: 25 October 1989
PDF: 6 pages
Proc. SPIE 1134, Optical Pattern Recognition II, (25 October 1989); doi: 10.1117/12.961610
Show Author Affiliations
M. Ibrahim Sezan, Eastman Kodak Co. (United States)
Henry Stark, Illinois Institute of Technology (United States)
Shu-Jen Yeh, Illinois Institute of Technology (United States)

Published in SPIE Proceedings Vol. 1134:
Optical Pattern Recognition II
H. John Caulfield, Editor(s)

© SPIE. Terms of Use
Back to Top