ML Anthology

Structural Risk Minimization for Character Recognition

I. Guyon, V. Vapnik, B. Boser, L. Bottou, S. A. Solla
NeurIPS 1991 pp. 471-479
/neurips/1991/guyon1991neurips-structural/

Abstract

The method of Structural Risk Minimization refers to tuning the capacity of the classifier to the available amount of training data. This capac(cid:173) ity is influenced by several factors, including: (1) properties of the input space, (2) nature and structure of the classifier, and (3) learning algorithm. Actions based on these three factors are combined here to control the ca(cid:173) pacity of linear classifiers and improve generalization on the problem of handwritten digit recognition.

PDF NeurIPS Semantic Scholar

Cite

Text

Guyon et al. "Structural Risk Minimization for Character Recognition." Neural Information Processing Systems, 1991.

Markdown

[Guyon et al. "Structural Risk Minimization for Character Recognition." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/guyon1991neurips-structural/)

BibTeX

@inproceedings{guyon1991neurips-structural,
  title     = {{Structural Risk Minimization for Character Recognition}},
  author    = {Guyon, I. and Vapnik, V. and Boser, B. and Bottou, L. and Solla, S. A.},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {471-479},
  url       = {https://mlanthology.org/neurips/1991/guyon1991neurips-structural/}
}