ML Anthology

Dynamics of Learning in Recurrent Feature-Discovery Networks

Todd K. Leen
NeurIPS 1990 pp. 70-76
/neurips/1990/leen1990neurips-dynamics/

Abstract

The self-organization of recurrent feature-discovery networks is studied from the perspective of dynamical systems. Bifurcation theory reveals pa(cid:173) rameter regimes in which multiple equilibria or limit cycles coexist with the equilibrium at which the networks perform principal component analysis.

PDF NeurIPS Semantic Scholar

Cite

Text

Leen. "Dynamics of Learning in Recurrent Feature-Discovery Networks." Neural Information Processing Systems, 1990.

Markdown

[Leen. "Dynamics of Learning in Recurrent Feature-Discovery Networks." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/leen1990neurips-dynamics/)

BibTeX

@inproceedings{leen1990neurips-dynamics,
  title     = {{Dynamics of Learning in Recurrent Feature-Discovery Networks}},
  author    = {Leen, Todd K.},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {70-76},
  url       = {https://mlanthology.org/neurips/1990/leen1990neurips-dynamics/}
}