Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
The Importance of Diversity in Neural Network Ensembles: An Empirical Investigation
Högskolan i Borås, Institutionen Handels- och IT-högskolan.ORCID-id: 0000-0003-0412-6199
Högskolan i Borås, Institutionen Handels- och IT-högskolan.ORCID-id: 0000-0003-0274-9026
2007 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

When designing ensembles, it is almost an axiom that the base classifiers must be diverse in order for the ensemble to generalize well. Unfortunately, there is no clear definition of the key term diversity, leading to several diversity measures and many, more or less ad hoc, methods for diversity creation in ensembles. In addition, no specific diversity measure has shown to have a high correlation with test set accuracy. The purpose of this paper is to empirically evaluate ten different diversity measures, using neural network ensembles and 11 publicly available data sets. The main result is that all diversity measures evaluated, in this study too, show low or very low correlation with test set accuracy. Having said that, two measures; double fault and difficulty show slightly higher correlations compared to the other measures. The study furthermore shows that the correlation between accuracy measured on training or validation data and test set accuracy also is rather low. These results challenge ensemble design techniques where diversity is explicitly maximized or where ensemble accuracy on a hold-out set is used for optimization.

Ort, förlag, år, upplaga, sidor
IEEE, 2007.
Nyckelord [en]
diversity, ensembles, neural networks, data mining
Nationell ämneskategori
Systemvetenskap, informationssystem och informatik
Identifikatorer
URN: urn:nbn:se:hj:diva-45818DOI: 10.1109/IJCNN.2007.4371035Lokalt ID: 0;0;miljJAILISBN: 1-4244-1380-X (tryckt)OAI: oai:DiVA.org:hj-45818DiVA, id: diva2:1348824
Konferens
The International Joint Conference on Neural Networks
Tillgänglig från: 2015-12-22 Skapad: 2019-09-05Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Johansson, UlfLöfström, Tuve

Sök vidare i DiVA

Av författaren/redaktören
Johansson, UlfLöfström, Tuve
Systemvetenskap, informationssystem och informatik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 4 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf