ML Anthology

Stable Dynamic Parameter Adaption

Stefan M. Rüger
NeurIPS 1995 pp. 225-231
/neurips/1995/ruger1995neurips-stable/

Abstract

A stability criterion for dynamic parameter adaptation is given. In the case of the learning rate of backpropagation, a class of stable algorithms is presented and studied, including a convergence proof.

PDF NeurIPS Semantic Scholar

Cite

Text

Rüger. "Stable Dynamic Parameter Adaption." Neural Information Processing Systems, 1995.

Markdown

[Rüger. "Stable Dynamic Parameter Adaption." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/ruger1995neurips-stable/)

BibTeX

@inproceedings{ruger1995neurips-stable,
  title     = {{Stable Dynamic Parameter Adaption}},
  author    = {Rüger, Stefan M.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {225-231},
  url       = {https://mlanthology.org/neurips/1995/ruger1995neurips-stable/}
}