Alternating projection neural networks
Robert J. Marks, Sung‐Kwun Oh, Les Atlas · IEEE Transactions on Circuits and Systems · 1989
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.>