DocumentCode
1442559
Title
Alternating projection neural networks
Author
Marks, Robert J., II ; Oh, Seho ; Atlas, Les E.
Author_Institution
Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
Volume
36
Issue
6
fYear
1989
fDate
6/1/1989 12:00:00 AM
Firstpage
846
Lastpage
857
Abstract
The authors consider a class of neural networks whose performance can be analyzed and geometrically visualized in a signal space environment. Alternating projection neural networks (APNNs) perform by alternatively projecting between two or more constraint sets. Criteria for desired and unique convergence are easily established. The network can be configured as either a content-addressable memory or classifier. Convergence of the APNN can be improved by the use of sigmoid-type nonlinearities and/or increasing the number of neurons in a hidden layer
Keywords
analogue computer circuits; computerised pattern recognition; content-addressable storage; convergence; memory architecture; neural nets; alternating projection type; classifier; content-addressable memory; convergence; neural networks; neurons; pattern-recognition; sigmoid-type nonlinearities; signal space environment; Associative memory; Clamps; Convergence; Interactive systems; Libraries; Neural networks; Neurons; Performance analysis; Signal analysis; Visualization;
fLanguage
English
Journal_Title
Circuits and Systems, IEEE Transactions on
Publisher
ieee
ISSN
0098-4094
Type
jour
DOI
10.1109/31.90404
Filename
90404
Link To Document