Difference between revisions of "Publications:Using Unlabelled Data to Train a Multilayer Perceptron"

From ISLAB/CAISR
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Antanas Verikas, Adas Gelzinis, Kerstin Malmqvist, Marija Bacauskiene |PID=...")
 
(No difference)

Latest revision as of 22:22, 11 February 2020

Do not edit this section

Keep all hand-made modifications below

Title Using Unlabelled Data to Train a Multilayer Perceptron
Author Antanas Verikas and Adas Gelzinis and Kerstin Malmqvist and Marija Bacauskiene
Year 2001
PublicationType Conference Paper
Journal
HostPublication Advances in Pattern Recognition — ICAPR 2001 : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings
Conference Conference of 2nd International Conference on Advances in Pattern Recognition (ICAPR 2001), Rio de Janeiro, Brazil, March 11-14, 2001
DOI http://dx.doi.org/10.1007/3-540-44732-6_5
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:1392758
Abstract This paper presents an approach to using both labelled and unlabelled data to train a multilayer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not represent adequately the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train neural networks for learning different classification problems. © Springer-Verlag Berlin Heidelberg 2001.