Using the Perceptron Algorithm to Find Consistent Hypotheses
Using the Perceptron Algorithm to Find Consistent Hypotheses
The perceptron learning algorithm yields quite naturally an algorithm for finding a linearly separable boolean function consistent with a sample of such a function. Using the idea of a specifying sample, we give a simple proof that this algorithm is not efficient, in general.
385-387
Anthony, M.
44cc9b8c-f199-4df9-a6c5-8b4a37c238b2
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
1993
Anthony, M.
44cc9b8c-f199-4df9-a6c5-8b4a37c238b2
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Anthony, M. and Shawe-Taylor, J.
(1993)
Using the Perceptron Algorithm to Find Consistent Hypotheses.
Combinatorics, Probability and Computing, 2, .
Abstract
The perceptron learning algorithm yields quite naturally an algorithm for finding a linearly separable boolean function consistent with a sample of such a function. Using the idea of a specifying sample, we give a simple proof that this algorithm is not efficient, in general.
More information
Published date: 1993
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259818
URI: http://eprints.soton.ac.uk/id/eprint/259818
PURE UUID: 5f961608-d236-4be0-9d1a-161aea429059
Catalogue record
Date deposited: 24 Aug 2004
Last modified: 14 Mar 2024 06:28
Export record
Contributors
Author:
M. Anthony
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