Show simple item record

dc.contributor.authorCunningham, Padraig
dc.date.accessioned2008-01-07T11:43:24Z
dc.date.available2008-01-07T11:43:24Z
dc.date.issued2000-02
dc.identifier.citationCunningham, Padraig. 'Overfitting and Diversity in Classification Ensembles based on Feature Selection'. - Dublin, Trinity College Dublin, Department of Computer Science, TCD-CS-2000-07, 2000, pp8en
dc.identifier.otherTCD-CS-2000-07
dc.identifier.urihttp://hdl.handle.net/2262/13078
dc.description.abstractThis paper addresses Wrapper-like approaches to feature subset selection and the production of classifier ensembles based on members with different feature subsets. The paper starts with the observation that if an insufficient amount of data is used to guide the Wrapper search then the feature selection will overfit the data. If the objective of the feature selection exercise is to build a better predictor, rather than identify important features for data mining reasons, then ensembles offers a solution. Overfitting may be used to provide diversity in ensembles provided the overfitted members have variety. The paper concludes with an assessment of entropy as a measure of diversity in classifier ensembles. A tentative conclusion is that diversity is not such a problem where a large number of features is involved but needs to be monitored for problems with smaller numbers of features ? say less than 25.en
dc.format.extent55767 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherTrinity College Dublin, Department of Computer Scienceen
dc.relation.ispartofseriesComputer Science Technical Reporten
dc.relation.ispartofseriesTCD-CS-2000-07en
dc.relation.haspartTCD-CS-[no.]en
dc.subjectComputer Scienceen
dc.titleOverfitting and Diversity in Classification Ensembles based on Feature Selectionen
dc.typeTechnical Reporten
dc.identifier.rssurihttps://www.cs.tcd.ie/publications/tech-reports/reports.00/TCD-CS-2000-07.pdf


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record