English

Dynamics of Learning with Restricted Training Sets I: General Theory

Disordered Systems and Neural Networks 2009-10-31 v1

Abstract

We study the dynamics of supervised learning in layered neural networks, in the regime where the size pp of the training set is proportional to the number NN 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 α=p/N\alpha=p/N\to\infty as a special case. For simplicity we restrict ourselves in this paper to single-layer networks and realizable tasks.

Keywords

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

R2 v1 2026-07-22T12:15:12.365Z