Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods

Abstract

In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.

Cite

Text

Haussler et al. "Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods." Neural Information Processing Systems, 1991.

Markdown

[Haussler et al. "Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/haussler1991neurips-estimating/)

BibTeX

@inproceedings{haussler1991neurips-estimating,
  title     = {{Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods}},
  author    = {Haussler, David and Kearns, Michael and Opper, Manfred and Schapire, Robert},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {855-862},
  url       = {https://mlanthology.org/neurips/1991/haussler1991neurips-estimating/}
}