Dynamics of Supervised Learning with Restricted Training Sets and Noisy Teachers
Abstract
We generalize a recent formalism to describe the dynamics of supervised learning in layered neural networks, in the regime where data recycling is inevitable, to the case of noisy teachers. Our theory generates reliable predictions for the evolution in time of training- and generalization er(cid:173) rors, and extends the class of mathematically solvable learning processes in large neural networks to those situations where overfitting can occur.
Cite
Text
Coolen and Mace. "Dynamics of Supervised Learning with Restricted Training Sets and Noisy Teachers." Neural Information Processing Systems, 1999.Markdown
[Coolen and Mace. "Dynamics of Supervised Learning with Restricted Training Sets and Noisy Teachers." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/coolen1999neurips-dynamics/)BibTeX
@inproceedings{coolen1999neurips-dynamics,
title = {{Dynamics of Supervised Learning with Restricted Training Sets and Noisy Teachers}},
author = {Coolen, Anthony C. C. and Mace, C. W. H.},
booktitle = {Neural Information Processing Systems},
year = {1999},
pages = {237-243},
url = {https://mlanthology.org/neurips/1999/coolen1999neurips-dynamics/}
}