- -

EvoDeep: A new evolutionary approach for automatic Deep Neural Networks parametrisation

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

EvoDeep: A new evolutionary approach for automatic Deep Neural Networks parametrisation

Show simple item record

Files in this item

dc.contributor.author Martín, Alejandro es_ES
dc.contributor.author Lara-Cabrera, Raúl es_ES
dc.contributor.author Fuentes-Hurtado, Félix José es_ES
dc.contributor.author Naranjo Ornedo, Valeriana es_ES
dc.contributor.author Camacho, David es_ES
dc.date.accessioned 2020-06-12T03:32:44Z
dc.date.available 2020-06-12T03:32:44Z
dc.date.issued 2018-07 es_ES
dc.identifier.issn 0743-7315 es_ES
dc.identifier.uri http://hdl.handle.net/10251/146154
dc.description.abstract [EN] Deep Neural Networks (DNN) have become a powerful, and extremely popular mechanism, which has been widely used to solve problems of varied complexity, due to their ability to make models fitted to non-linear complex problems. Despite its well-known benefits, DNNs are complex learning models whose parametrisation and architecture are made usually by hand. This paper proposes a new Evolutionary Algorithm, named EvoDeep. devoted to evolve the parameters and the architecture of a DNN in order to maximise its classification accuracy, as well as maintaining a valid sequence of layers. This model is tested against a widely used dataset of handwritten digits images. The experiments performed using this dataset show that the Evolutionary Algorithm is able to select the parameters and the DNN architecture appropriately, achieving a 98.93% accuracy in the best run. (C) 2017 Elsevier Inc. All rights reserved. es_ES
dc.description.sponsorship This work has been co-funded by the next research projects: EphemeCH (TIN2014-56494-C4-4-P) and DeepBio (TIN2017-85727-C4-3-P) Spanish Ministry of Economy and Competitivity and European Regional Development Fund FEDER, Justice Programme of the European Union (2014-2020) 723180 -RiskTrack-JUST-2015-JCOO-AG/JUST-2015-JCOO-AG-1, and by the CAM grant S2013/ICE-3095 (CIBERDINE:Cybersecurity, Data and Risks). The contents of this publication are the sole responsibility of their authors and can in no way be taken to reflect the views of the European Commission. es_ES
dc.language Inglés es_ES
dc.publisher Elsevier es_ES
dc.relation info:eu-repo/grantAgreement/MINECO//TIN2014-56494-C4-4-P/ES/ALGORITMOS BIOINSPIRADOS EN ENTORNOS EFIMEROS COMPLEJOS/ es_ES
dc.relation MINECO/TIN2017-85727-C4-3-P es_ES
dc.relation EC/723180 es_ES
dc.relation CAM/S2013/ICE-3095 es_ES
dc.relation.ispartof Journal of Parallel and Distributed Computing es_ES
dc.rights Reserva de todos los derechos es_ES
dc.subject Deep learning es_ES
dc.subject Evolutionary algorithms es_ES
dc.subject Finite-State machines es_ES
dc.subject Automated parametrisation es_ES
dc.subject.classification TEORIA DE LA SEÑAL Y COMUNICACIONES es_ES
dc.title EvoDeep: A new evolutionary approach for automatic Deep Neural Networks parametrisation es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1016/j.jpdc.2017.09.006 es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Comunicaciones - Departament de Comunicacions es_ES
dc.description.bibliographicCitation Martín, A.; Lara-Cabrera, R.; Fuentes-Hurtado, FJ.; Naranjo Ornedo, V.; Camacho, D. (2018). EvoDeep: A new evolutionary approach for automatic Deep Neural Networks parametrisation. Journal of Parallel and Distributed Computing. 117:180-191. https://doi.org/10.1016/j.jpdc.2017.09.006 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion https://doi.org/10.1016/j.jpdc.2017.09.006 es_ES
dc.description.upvformatpinicio 180 es_ES
dc.description.upvformatpfin 191 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 117 es_ES
dc.relation.pasarela S\350444 es_ES
dc.contributor.funder Comunidad de Madrid es_ES
dc.contributor.funder European Commission es_ES
dc.contributor.funder European Regional Development Fund es_ES
dc.contributor.funder Ministerio de Economía y Competitividad es_ES


This item appears in the following Collection(s)

Show simple item record