hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Using unlabelled data to train a multilayer perceptron
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).ORCID iD: 0000-0003-2185-8973
Kaunas University of Technology, Lithuania.
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
2001 (English)In: Neural Processing Letters, ISSN 1370-4621, E-ISSN 1573-773X, Vol. 14, no 3, p. 179-201Article in journal (Refereed) Published
Abstract [en]

This Letter 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 adequately represent 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.

Place, publisher, year, edition, pages
New York: Springer, 2001. Vol. 14, no 3, p. 179-201
Keywords [en]
Artificial neural networks, Classification, Multiplayer perceptron, Supervised learning, Unlabelled data
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:hh:diva-3539DOI: 10.1023/A:1012707515770ISI: 000172073000002Scopus ID: 2-s2.0-0035576170OAI: oai:DiVA.org:hh-3539DiVA, id: diva2:286834
Available from: 2010-01-15 Created: 2009-12-01 Last updated: 2021-04-06Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Verikas, AntanasMalmqvist, Kerstin

Search in DiVA

By author/editor
Verikas, AntanasMalmqvist, Kerstin
By organisation
Halmstad Embedded and Intelligent Systems Research (EIS)Intelligent systems (IS-lab)
In the same journal
Neural Processing Letters
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 307 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf