The University of Southampton
University of Southampton Institutional Repository

Generalisation Analysis for Classes of Continuous Neural Networks

Generalisation Analysis for Classes of Continuous Neural Networks
Generalisation Analysis for Classes of Continuous Neural Networks
This paper reviews some of the recent results in applying the theory of Probably Approximately Correct (PAC) learning to feedforward neural networks with continuous activation functions. Despite the best-known upper bound on the VC dimension of sigmoid networks being O((WN)’), for W parameters and N computational nodes, at is shown that the asymptotic bound on the sample size required for learning sigmoid networks is better than would be expected from a naive use of the VC dimension result. We propose a way of using boolean circuits to perform real valued computation in a way that naturally extends their boolean functionality. The functionality of multiple fans in threshold gates in this model is shown to mimic that of a hardware implementation of continuous Neural Networks. The sample sizes obtained for these networks are significantly lower than those obtained for sigmoidal networks.
0780327683
2944-2948
IEEE
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b

Shawe-Taylor, John (1995) Generalisation Analysis for Classes of Continuous Neural Networks. In Proceedings of ICNN'95 International Conference on Neural Networks. IEEE. pp. 2944-2948 .

Record type: Conference or Workshop Item (Paper)

Abstract

This paper reviews some of the recent results in applying the theory of Probably Approximately Correct (PAC) learning to feedforward neural networks with continuous activation functions. Despite the best-known upper bound on the VC dimension of sigmoid networks being O((WN)’), for W parameters and N computational nodes, at is shown that the asymptotic bound on the sample size required for learning sigmoid networks is better than would be expected from a naive use of the VC dimension result. We propose a way of using boolean circuits to perform real valued computation in a way that naturally extends their boolean functionality. The functionality of multiple fans in threshold gates in this model is shown to mimic that of a hardware implementation of continuous Neural Networks. The sample sizes obtained for these networks are significantly lower than those obtained for sigmoidal networks.

This record has no associated files available for download.

More information

Published date: 1995
Organisations: Electronics & Computer Science

Identifiers

Local EPrints ID: 259687
URI: http://eprints.soton.ac.uk/id/eprint/259687
ISBN: 0780327683
PURE UUID: 126efba5-9e81-4d9c-9af5-afd4f0a61570

Catalogue record

Date deposited: 05 Aug 2004
Last modified: 20 Jul 2022 16:31

Export record

Contributors

Author: John 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

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×