Measuring the VC-dimension of a learning machine (1994) [29 citations — 2 self]
Download:
|
|
by Vladimir Vapnik, Esther Levin, Yann Le Cun
Neural Computation
http://www.research.att.com/~yann/exdb/publis/./psgz/vapnik-levin-lecun-94.ps.gz
Add To MetaCart
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
@ARTICLE{Vapnik94measuringthe,author = {Vladimir Vapnik and Esther Levin and Yann Le Cun},
title = {Measuring the VC-dimension of a learning machine},
journal = {Neural Computation},
year = {1994},
volume = {6},
pages = {851--876}
}
Years of Citing Articles
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.
Citations
| 654 | On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab – Vapnik, Červonekis - 1971 |
| 637 | Estinwtion of Dependences Based on Empirical Data – Vapnik - 1982 |
| 350 | Optimal brain damage – Cun, Denker, et al. - 1990 |
| 35 | Structural risk minimization for character recognition – Guyon, Vapnik, et al. - 1992 |
| 25 | The necessary and sufficient conditions for consistency in the empirical risk minimizatin method – Vapnik, Chervonenkis - 1991 |
| 18 | Hints and the VC dimension – Abu-Mostafa - 1993 |
| 17 | Bounds for the uniform deviation of empirical measures – Devroye - 1982 |
| 2 | Private communication – Cortés - 2002 |
