Publication: Moving away from error-based learning in multi-objective estimation of distribution algorithms
dc.affiliation.dpto | UC3M. Departamento de Informática | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA) | es |
dc.contributor.author | Martí, Luis | |
dc.contributor.author | García, Jesús | |
dc.contributor.author | Berlanga de Jesús, Antonio | |
dc.contributor.author | Molina López, José Manuel | |
dc.date.accessioned | 2014-03-28T11:32:44Z | |
dc.date.available | 2014-03-28T11:32:44Z | |
dc.date.issued | 2010-07 | |
dc.description | Proceedings of: 12th annual conference on Genetic and evolutionary computation (GECCO '10). Portland, Oregon, USA, July 7-11, 2010. | es |
dc.description.abstract | In this work we analyze the model-building issue and the requirements it imposes on the learning paradigm being used. We argue that error-based learning, the class of learning most commonly used in MOEDAs, is responsible for current MOEDA underachievement. We present ART as a viable alternative and present a novel algorithm called multi-objective ART-based EDA (MARTEDA) that uses a Gaussian ART neural network for model-building and an hypervolume based selector as described for the HypE algorithm. We experimentally show that thanks to MARTEDA's novel model-building approach and an indicator-based population ranking the algorithm it is able to outperform similar MOEDAs and MOEAs. | es |
dc.description.sponsorship | This work was supported in part by projects CICYT TIN2008-06742-C02-02/TSI, CICYT TEC2008-06732-C02-02/TEC, DPS2008-07029-C02-02 and CAM CONTEXTS S2009/TIC-1485. | es |
dc.description.status | Publicado | es |
dc.format.mimetype | application/pdf | |
dc.identifier.bibliographicCitation | GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computation. (2010) ACM, New York, USA, 545-546 | es |
dc.identifier.doi | 10.1145/1830483.1830585 | |
dc.identifier.isbn | 978-1-4503-0072-8 | |
dc.identifier.publicationfirstpage | 545 | |
dc.identifier.publicationlastpage | 546 | |
dc.identifier.publicationtitle | GECCO 2010 : Genetic and Evolutionary Computation Conference : Wednesday-Sunday, July 7-11, 2010, Portland, Oregon | |
dc.identifier.uri | https://hdl.handle.net/10016/18667 | |
dc.identifier.uxxi | CC/0000011615 | |
dc.language.iso | eng | es |
dc.publisher | ACM | es |
dc.relation.eventdate | July 7-11, 2010 | es |
dc.relation.eventnumber | 12 | |
dc.relation.eventplace | Portland, Oregon, USA | es |
dc.relation.eventtitle | Conference on Genetic and evolutionary computation (GECCO '10) | es |
dc.relation.projectID | Comunidad de Madrid. S2009/TIC-1485/CONTEXTS | es |
dc.rights | © ACM, 2010 | es |
dc.rights.accessRights | open access | es |
dc.subject.eciencia | Informática | es |
dc.subject.other | Multi-objective Optimization | es |
dc.subject.other | Estimation of Distribution Algorithms | es |
dc.subject.other | Adaptive Resonance Theory | es |
dc.title | Moving away from error-based learning in multi-objective estimation of distribution algorithms | es |
dc.type | conference paper | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1