Mostrar el registro sencillo del ítem

dc.contributor.authorCamero, Andrés
dc.contributor.authorToutouh, Jamal
dc.contributor.authorAlba, Enrique
dc.date.accessioned2018-11-26T10:40:41Z
dc.date.available2018-11-26T10:40:41Z
dc.date.created2018
dc.date.issued2018-11-26
dc.identifier.urihttps://hdl.handle.net/10630/16952
dc.description.abstractRecurrent neural networks have demonstrated to be good at tackling prediction problems, however due to their high sensitivity to hyper-parameter configuration, finding an appropriate network is a tough task. Automatic hyper-parameter optimization methods have emerged to find the most suitable configuration to a given problem, but these methods are not generally adopted because of their high computational cost. Therefore, in this study we extend the MAE random sampling, a low-cost method to compare single-hidden layer architectures, to multiple-hidden-layer ones. We validate empirically our proposal and show that it is possible to predict and compare the expected performance of an hyper-parameter configuration in a low-cost way.en_US
dc.description.sponsorshipUniversidad de Málaga. Campus de Excelencia Internacional Andalucía Tech. This research was partially funded by Ministerio de Economı́a, Industria y Competitividad, Gobierno de España, and European Regional Development Fund grant numbers TIN2016-81766-REDT (http://cirti.es) and TIN2017-88213-R (http://6city.lcc.uma.es).en_US
dc.language.isoengen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectInteligencia artificialen_US
dc.subject.otherDeep learningen_US
dc.subject.otherRecurrent neural networken_US
dc.subject.otherMAE random samplingen_US
dc.titleComparing Deep Recurrent Networks Based on the MAE Random Sampling, a First Approachen_US
dc.typeinfo:eu-repo/semantics/conferenceObjecten_US
dc.centroE.T.S.I. Informáticaen_US
dc.relation.eventtitleConference of the Spanish Association for Artificial Intelligence (CAEPIA)en_US
dc.relation.eventplaceGranada, Españaen_US
dc.relation.eventdate23-26 de octubre de 2018en_US


Ficheros en el ítem

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

Mostrar el registro sencillo del ítem