Bounding Sample Size with the Vapnik-Chervonenkis Dimension


Shawe-Taylor, J., Anthony, M. and Biggs, N.L. (1993) Bounding Sample Size with the Vapnik-Chervonenkis Dimension. Discrete Applied Mathematics, 42, (1), 65-73.

Download

[img] PDF
Download (119Kb)

Description/Abstract

A proof that a concept class is learnable provided the Vapnik—Chervonenkis dimension is finite is given. The proof is more explicit than previous proofs and introduces two new parameters which allow bounds on the sample size obtained to be improved by a factor of approximately 4 log2(e).

Item Type: Article
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 259820
Date Deposited: 24 Aug 2004
Last Modified: 27 Mar 2014 20:02
Further Information:Google Scholar
ISI Citation Count:16
URI: http://eprints.soton.ac.uk/id/eprint/259820

Actions (login required)

View Item View Item