ML Anthology

Measuring the VC-Dimension of a Learning Machine

Vladimir Vapnik, Esther Levin, Yann LeCun
NeCo 1994 pp. 851-876
doi:10.1162/NECO.1994.6.5.851 /neco/1994/vapnik1994neco-measuring/

Abstract

A method for measuring the capacity of learning machines is described. The method is based on fitting a theoretically derived function to empirical measurements of the maximal difference between the error rates on two separate data sets of varying sizes. Experimental measurements of the capacity of various types of linear classifiers are presented.

NeCo Semantic Scholar

Cite

Text

Vapnik et al. "Measuring the VC-Dimension of a Learning Machine." Neural Computation, 1994. doi:10.1162/NECO.1994.6.5.851

Markdown

[Vapnik et al. "Measuring the VC-Dimension of a Learning Machine." Neural Computation, 1994.](https://mlanthology.org/neco/1994/vapnik1994neco-measuring/) doi:10.1162/NECO.1994.6.5.851

BibTeX

@article{vapnik1994neco-measuring,
  title     = {{Measuring the VC-Dimension of a Learning Machine}},
  author    = {Vapnik, Vladimir and Levin, Esther and LeCun, Yann},
  journal   = {Neural Computation},
  year      = {1994},
  pages     = {851-876},
  doi       = {10.1162/NECO.1994.6.5.851},
  volume    = {6},
  url       = {https://mlanthology.org/neco/1994/vapnik1994neco-measuring/}
}