Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

July 1, 2001, Vol. 13, No. 7, Pages 1625-1647
(doi: 10.1162/089976601750265036)
© 2001 Massachusetts Institute of Technology
A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold
Article PDF (113.69 KB)
Abstract

Recently we introduced the concept of neural network learning on Stiefel-Grassman manifold for multilayer perceptron—like networks. Contributions of other authors have also appeared in the scientific literature about this topic. This article presents a general theory for it and illustrates how existing theories may be explained within the general framework proposed here.