Sample Sizes for Multiple Output Threshold Networks
Sample Sizes for Multiple Output Threshold Networks
This paper applies the theory of probably approximately correct (PAC) learning to multiple-output feedforward threshold networks. It is shown that the sample size for reliable learning can be bounded above by a quantity independent of the number of outputs of the network.
107-117
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Anthony, M.
44cc9b8c-f199-4df9-a6c5-8b4a37c238b2
1991
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Anthony, M.
44cc9b8c-f199-4df9-a6c5-8b4a37c238b2
Shawe-Taylor, J. and Anthony, M.
(1991)
Sample Sizes for Multiple Output Threshold Networks.
Network, 2 (1), .
Abstract
This paper applies the theory of probably approximately correct (PAC) learning to multiple-output feedforward threshold networks. It is shown that the sample size for reliable learning can be bounded above by a quantity independent of the number of outputs of the network.
Text
SampleSizesForMultipleOutput.pdf
- Other
More information
Published date: 1991
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259827
URI: http://eprints.soton.ac.uk/id/eprint/259827
ISSN: 0954-898x
PURE UUID: e36ba8c7-c7ff-49df-a816-61239e3fbd9d
Catalogue record
Date deposited: 24 Aug 2004
Last modified: 14 Mar 2024 06:28
Export record
Contributors
Author:
J. Shawe-Taylor
Author:
M. Anthony
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