Sample Sizes for Threshold Networks with Equivalences
Sample Sizes for Threshold Networks with Equivalences
This paper applies the theory of Probably Approximately Correct (PAC) learning to multiple output feedforward threshold networks in which the weights conform to certain equivalences. It is shown that the sample site for reliable learning can be bounded above by a formula similar to that required for single output networks with no equivalences. The best previously obtained bounds are improved for all cases.
65-72
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
April 1995
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Shawe-Taylor, J.
(1995)
Sample Sizes for Threshold Networks with Equivalences.
Information and Computation, 118 (1), .
Abstract
This paper applies the theory of Probably Approximately Correct (PAC) learning to multiple output feedforward threshold networks in which the weights conform to certain equivalences. It is shown that the sample site for reliable learning can be bounded above by a formula similar to that required for single output networks with no equivalences. The best previously obtained bounds are improved for all cases.
Text
SampleSizesForThresholdNetworksWithEquivalences.pdf
- Other
More information
Published date: April 1995
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259808
URI: http://eprints.soton.ac.uk/id/eprint/259808
ISSN: 0890-5401
PURE UUID: 391a75b7-4097-4728-8f40-d2124f4ddc55
Catalogue record
Date deposited: 23 Aug 2004
Last modified: 14 Mar 2024 06:28
Export record
Contributors
Author:
J. Shawe-Taylor
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