Sample Sizes for Threshold Networks with Equivalences


Shawe-Taylor, J. (1995) Sample Sizes for Threshold Networks with Equivalences. Information and Computation, 118, (1), 65-72.

Download

[img] PDF
Download (566Kb)

Description/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.

Item Type: Article
ISSNs: 0890-5401
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 259808
Date Deposited: 23 Aug 2004
Last Modified: 27 Mar 2014 20:02
Further Information:Google Scholar
ISI Citation Count:4
URI: http://eprints.soton.ac.uk/id/eprint/259808

Actions (login required)

View Item View Item

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