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
fDate :
6/1/1989 12:00:00 AM
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;
Journal_Title :
Circuits and Systems, IEEE Transactions on
