Optimizing linear and quadratic data transformations for classification tasks

Valls, José M.; Aler, Ricardo

Publication:
Optimizing linear and quadratic data transformations for classification tasks

dc.affiliation.dpto	UC3M. Departamento de Informática	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)	es
dc.contributor.author	Valls, José M.
dc.contributor.author	Aler, Ricardo
dc.date.accessioned	2010-01-25T11:25:02Z
dc.date.accessioned	2010-03-22T16:47:09Z
dc.date.available	2010-01-25T11:25:02Z
dc.date.available	2010-03-22T16:47:09Z
dc.date.issued	2009
dc.description	Proceeding of: Ninth International Conference on Intelligent Systems Design and Applications, 2009. ISDA '09. Nov. 30 2009-Dec. 2, 2009
dc.description.abstract	Many classification algorithms use the concept of distance or similarity between patterns. Previous work has shown that it is advantageous to optimize general Euclidean distances (GED). In this paper, we optimize data transformations, which is equivalent to searching for GEDs, but can be applied to any learning algorithm, even if it does not use distances explicitly. Two optimization techniques have been used: a simple Local Search (LS) and the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). CMA-ES is an advanced evolutionary method for optimization in difficult continuous domains. Both diagonal and complete matrices have been considered. The method has also been extended to a quadratic non-linear transformation. Results show that in general, the transformation methods described here either outperform or match the classifier working on the original data.
dc.description.sponsorship	This work has been funded by the Spanish Ministry of Science under contract TIN2008-06491-C04-03 (MSTAR project)
dc.description.status	Publicado
dc.format.mimetype	application/pdf
dc.format.mimetype	text/plain
dc.format.mimetype	application/octet-stream
dc.format.mimetype	application/octet-stream
dc.format.mimetype	application/octet-stream
dc.format.mimetype	application/pdf
dc.identifier.bibliographicCitation	Ninth International Conference on Intelligent Systems Design and Applications, 2009. ISDA'09. pp. 1025 - 1030
dc.identifier.doi	10.1109/ISDA.2009.222
dc.identifier.isbn	978-0-7695-3872-3
dc.identifier.publicationfirstpage	1025
dc.identifier.publicationlastpage	1030
dc.identifier.publicationtitle	Ninth International Conference on Intelligent Systems Design and Applications, 2009. ISDA'09
dc.identifier.uri	https://hdl.handle.net/10016/6604
dc.language.iso	eng
dc.publisher	IEEE
dc.relation.eventdate	Nov. 30 2009-Dec. 2, 2009
dc.relation.eventnumber	9
dc.relation.eventplace	Pisa (Italy)
dc.relation.eventtitle	International Conference on Intelligent Systems Design and Applications, 2009. ISDA '09.
dc.relation.publisherversion	http://dx.doi.org/10.1109/ISDA.2009.222
dc.rights	© IEEE
dc.rights.accessRights	open access
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.eciencia	Informática
dc.subject.ofertatecnologica	Evolutionary-based machine learning
dc.subject.other	Data transformations
dc.subject.other	General euclidean distances
dc.subject.other	Evolutionary computation
dc.title	Optimizing linear and quadratic data transformations for classification tasks
dc.type	conference paper	*
dc.type.review	PeerReviewed
dspace.entity.type	Publication