Lossless fitness inheritance in genetic algorithms for decision trees

Simple item page
dc.creatorKalles, Dimitris
dc.creatorPapagelis, Athanassios
dc.date2006-11-30
dc.date2009-03-10
dc.date.accessioned2026-07-07T12:50:35Z
dc.date.available2026-07-07T12:50:35Z
dc.descriptionWhen genetic algorithms are used to evolve decision trees, key tree quality parameters can be recursively computed and re-used across generations of partially similar decision trees. Simply storing instance indices at leaves is enough for fitness to be piecewise computed in a lossless fashion. We show the derivation of the (substantial) expected speed-up on two bounding case problems and trace the attractive property of lossless fitness inheritance to the divide-and-conquer nature of decision trees. The theoretical results are supported by experimental evidence.
dc.descriptionContains 23 pages, 6 figures, 12 tables. Text last updated as of March 6, 2009. Submitted to a journal
dc.identifierhttps://arxiv.org/abs/cs/0611166
dc.identifierhttp://arxiv.org/abs/cs/0611166
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/222725
dc.subjectArtificial Intelligence
dc.subjectData Structures and Algorithms
dc.subjectNeural and Evolutionary Computing
dc.titleLossless fitness inheritance in genetic algorithms for decision trees
dc.typetext

Files

Collections

arXiv