Mostrar el registro sencillo del ítem

On the Problem of Error Propagation in classifier chains for multi-label classification

dc.contributor.authorSenge, Robin
dc.contributor.authorCoz Velasco, Juan José del 
dc.contributor.authorHüllermeier, Eyke
dc.date.accessioned2016-03-18T09:20:46Z
dc.date.available2016-03-18T09:20:46Z
dc.date.issued2013
dc.identifier.isbn978-3-319-01594-1
dc.identifier.isbn978-3-319-01595-8
dc.identifier.urihttp://hdl.handle.net/10651/35746
dc.description.abstractSo-called classifier chains have recently been proposed as an appealing method for tackling the multi-label classification task. In this paper, we analyze the influence of a potential pitfall of the learning process, namely the discrepancy between the feature spaces used in training and testing: While true class labels are used as supplementary attributes for training the binary models along the chain, the same models need to rely on estimations of these labels when making a prediction. We provide first experimental results suggesting that the attribute noise thus created can affect the overall prediction performance of a classifier chainspa
dc.description.sponsorshipThis research has been supported by the Germany Research Foundation (DFG) and the Spanish Ministerio de Ciencia e Innovación (MICINN) under grant TIN2011-23558spa
dc.format.extentp. 163-170spa
dc.language.isoengspa
dc.publisherSpringerspa
dc.relation.ispartofData Analysis, Machine Learning and Knowledge Discoveryspa
dc.rights© 2013 Springer
dc.titleOn the Problem of Error Propagation in classifier chains for multi-label classificationspa
dc.typebook partspa
dc.identifier.doi10.1007/978-3-319-01595-8_18
dc.relation.projectIDMEC/TIN2011-23558spa
dc.relation.publisherversionhttp://dx.doi.org/10.1007/978-3-319-01595-8_18spa
dc.rights.accessRightsopen access
dc.type.hasVersionAM


Ficheros en el ítem

untranslated

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem