Dynamics of Supervised Learning with Restricted Training Sets
Abstract
We study the dynamics of supervised learning in layered neural net(cid:173) works, in the regime where the size p of the training set is proportional to the number N of inputs. Here the local fields are no longer described by Gaussian distributions. We use dynamical replica theory to predict the evolution of macroscopic observables, including the relevant error measures, incorporating the old formalism in the limit piN --t 00.
Cite
Text
Coolen and Saad. "Dynamics of Supervised Learning with Restricted Training Sets." Neural Information Processing Systems, 1998.Markdown
[Coolen and Saad. "Dynamics of Supervised Learning with Restricted Training Sets." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/coolen1998neurips-dynamics/)BibTeX
@inproceedings{coolen1998neurips-dynamics,
title = {{Dynamics of Supervised Learning with Restricted Training Sets}},
author = {Coolen, Anthony C. C. and Saad, David},
booktitle = {Neural Information Processing Systems},
year = {1998},
pages = {197-203},
url = {https://mlanthology.org/neurips/1998/coolen1998neurips-dynamics/}
}