Measuring the VC-dimension of a learning machine

  • Authors:
  • Vladimir Vapnik;Esther Levin;Yann Le Cun

  • Affiliations:
  • -;-;-

  • Venue:
  • Neural Computation
  • Year:
  • 1994

Quantified Score

Hi-index 0.00

Visualization

Abstract

A method for measuring the capacity of learning machines isdescribed. The method is based on fitting a theoretically derivedfunction to empirical measurements of the maximal differencebetween the error rates on two separate data sets of varying sizes.Experimental measurements of the capacity of various types oflinear classifiers are presented.