hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Selecting features for neural network committees
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.ORCID iD: 0000-0003-2185-8973
Kaunas University of Technology, Department of Electric Power Systems, Kaunas, Lithuania.
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
2002 (English)In: Proceedings of the International Joint Conference on Neural Networks, Piscataway: IEEE, 2002, p. 215-220Conference paper, Published paper (Refereed)
Abstract [en]

We present a neural network based approach for identifying salient features for classification in neural network committees. Our approach involves neural network training with an augmented cross-entropy error function. The augmented error function forces the neural network to keep low derivatives of the transfer functions of neurons of the network when learning a classification task. Such an approach reduces output sensitivity to the input changes. Feature selection is based on the reaction of the cross-validation data set classification error due to the removal of the individual features. We compared the approach with two other neural network based feature selection methods. The algorithm developed outperformed the methods by achieving a higher classification accuracy on three real world problems tested. ©2002 IEEE

Place, publisher, year, edition, pages
Piscataway: IEEE, 2002. p. 215-220
National Category
Telecommunications
Identifiers
URN: urn:nbn:se:hh:diva-38119DOI: 10.1109/IJCNN.2002.1005472ISI: 000177402800040Scopus ID: 2-s2.0-0036076592ISBN: 0-7803-7278-6 (print)OAI: oai:DiVA.org:hh-38119DiVA, id: diva2:1254348
Conference
International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States, 12-17 May, 2002
Available from: 2018-10-09 Created: 2018-10-09 Last updated: 2018-10-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Verikas, AntanasMalmqvist, Kerstin

Search in DiVA

By author/editor
Verikas, AntanasMalmqvist, Kerstin
By organisation
CAISR - Center for Applied Intelligent Systems Research
Telecommunications

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 75 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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