Measuring the VC-Dimension of a Learning Machine
Vladimir N. Vapnika b, Esther Levina b, Yann LeCuna b
- aAT&T Bell Laboratories, Holmdel, NJ 07733 USA
- bAT&T Bell Laboratories, Holmdel. NJ 07733, USA
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
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.
TL;DRA method for measuring the capacity of learning machines is described, 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. (Semantic Scholar)