Measuring the VC-dimension of a learning machine
| Author(s) : | Yann Le Cun Esther Levin Vladimir Vapnik, |
| Publisher : | N/A |
| Publication Date : | 1994 |
| ISSN : | N/A |
| 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., |