Dynamics of On-Line Gradient Descent Learning for Multilayer Neural Networks

Abstract

We consider the problem of on-line gradient descent learning for general two-layer neural networks. An analytic solution is pre(cid:173) sented and used to investigate the role of the learning rate in con(cid:173) trolling the evolution and convergence of the learning process.

Cite

Text

Saad and Solla. "Dynamics of On-Line Gradient Descent Learning for Multilayer Neural Networks." Neural Information Processing Systems, 1995.

Markdown

[Saad and Solla. "Dynamics of On-Line Gradient Descent Learning for Multilayer Neural Networks." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/saad1995neurips-dynamics/)

BibTeX

@inproceedings{saad1995neurips-dynamics,
  title     = {{Dynamics of On-Line Gradient Descent Learning for Multilayer Neural Networks}},
  author    = {Saad, David and Solla, Sara A.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {302-308},
  url       = {https://mlanthology.org/neurips/1995/saad1995neurips-dynamics/}
}