Bounding Sample Size with the Vapnik-Chervonenkis Dimension
Bounding Sample Size with the Vapnik-Chervonenkis Dimension
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).
65-73
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Anthony, M.
44cc9b8c-f199-4df9-a6c5-8b4a37c238b2
Biggs, N.L.
d80f568d-d608-49dd-bd35-f4331c568aa4
1993
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Anthony, M.
44cc9b8c-f199-4df9-a6c5-8b4a37c238b2
Biggs, N.L.
d80f568d-d608-49dd-bd35-f4331c568aa4
Shawe-Taylor, J., Anthony, M. and Biggs, N.L.
(1993)
Bounding Sample Size with the Vapnik-Chervonenkis Dimension.
Discrete Applied Mathematics, 42 (1), .
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).
More information
Published date: 1993
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259820
URI: http://eprints.soton.ac.uk/id/eprint/259820
ISSN: 0166-218X
PURE UUID: fb563696-acff-40d2-a799-15c4d6c53258
Catalogue record
Date deposited: 24 Aug 2004
Last modified: 14 Mar 2024 06:28
Export record
Contributors
Author:
J. Shawe-Taylor
Author:
M. Anthony
Author:
N.L. Biggs
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics