A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold

Fiori, Simone G. O.

doi:10.1162/089976601750265036

A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold

Simone G. O. Fiori

NeCo 2001 pp. 1625-1647

doi:10.1162/089976601750265036 /neco/2001/fiori2001neco-theory/

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.

NeCo Semantic Scholar

Cite

Text

Fiori. "A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold." Neural Computation, 2001. doi:10.1162/089976601750265036

Markdown

[Fiori. "A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold." Neural Computation, 2001.](https://mlanthology.org/neco/2001/fiori2001neco-theory/) doi:10.1162/089976601750265036

BibTeX

@article{fiori2001neco-theory,
  title     = {{A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold}},
  author    = {Fiori, Simone G. O.},
  journal   = {Neural Computation},
  year      = {2001},
  pages     = {1625-1647},
  doi       = {10.1162/089976601750265036},
  volume    = {13},
  url       = {https://mlanthology.org/neco/2001/fiori2001neco-theory/}
}