Discovering Hidden Features with Gaussian Processes Regression
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
Vivarelli and Williams. "Discovering Hidden Features with Gaussian Processes Regression." Neural Information Processing Systems, 1998.Markdown
[Vivarelli and Williams. "Discovering Hidden Features with Gaussian Processes Regression." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/vivarelli1998neurips-discovering/)BibTeX
@inproceedings{vivarelli1998neurips-discovering,
title = {{Discovering Hidden Features with Gaussian Processes Regression}},
author = {Vivarelli, Francesco and Williams, Christopher K. I.},
booktitle = {Neural Information Processing Systems},
year = {1998},
pages = {613-619},
url = {https://mlanthology.org/neurips/1998/vivarelli1998neurips-discovering/}
}