Dynamics of Learning with Restricted Training Sets I: General Theory
Abstract
We study the dynamics of supervised learning in layered neural networks, in the regime where the size of the training set is proportional to the number of inputs. Here the local fields are no longer described by Gaussian probability distributions and the learning dynamics is of a spin-glass nature, with the composition of the training set playing the role of quenched disorder. We show how dynamical replica theory can be used to predict the evolution of macroscopic observables, including the two relevant performance measures (training error and generalization error), incorporating the old formalism developed for complete training sets in the limit as a special case. For simplicity we restrict ourselves in this paper to single-layer networks and realizable tasks.
Cite
@article{arxiv.cond-mat/9909402,
title = {Dynamics of Learning with Restricted Training Sets I: General Theory},
author = {A. C. C. Coolen and D. Saad},
journal= {arXiv preprint arXiv:cond-mat/9909402},
year = {2009}
}
Comments
39 pages, LaTeX