Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/55092
Campo DC Valoridioma
dc.contributor.authorMellouli, Dorraen_US
dc.contributor.authorHamdani, Tarek M.en_US
dc.contributor.authorSanchez-Medina, Javier J.en_US
dc.contributor.authorAyed, Mounir Benen_US
dc.contributor.authorAlimi, Adel M.en_US
dc.date.accessioned2019-02-18T16:28:55Z-
dc.date.available2019-02-18T16:28:55Z-
dc.date.issued2019en_US
dc.identifier.issn2162-237Xen_US
dc.identifier.urihttp://hdl.handle.net/10553/55092-
dc.description.abstractDeep neural networks have proved promising results in many applications and fields, but they are still assimilated to a black box. Thus, it is very useful to introduce interpretability aspects to prevent the blind application of deep networks. This paper proposed an interpretable morphological convolutional neural network called Morph-CNN for pattern recognition, where morphological operations were incorporated using counter-harmonic mean into the convolutional layer in order to generate enhanced feature maps. Morph-CNN was extensively evaluated on MNIST and SVHN benchmarks for digit recognition. The different tested configurations showed that Morph-CNN outperforms the existing methods.en_US
dc.languageengen_US
dc.publisher2162-237X-
dc.relation.ispartofIEEE Transactions on Neural Networks and Learning Systemsen_US
dc.sourceIEEE Transactions on Neural Networks and Learning Systems [ISSN 2162-237X], v. 30 (9), p. 2876 - 2885en_US
dc.subject120304 Inteligencia artificialen_US
dc.subject.otherConvolutional neural network (CNN)en_US
dc.subject.otherDeep neural networks (DNNs)en_US
dc.subject.otherImage recognitionen_US
dc.subject.otherInterpretabilityen_US
dc.subject.otherMorphological CNN (Morph-CNN)en_US
dc.subject.otherMorphological operatorsen_US
dc.titleMorphological convolutional neural network architecture for digit recognitionen_US
dc.typeinfo:eu-repo/semantics/Articleen_US
dc.typeArticlees
dc.identifier.doi10.1109/TNNLS.2018.2890334
dc.identifier.scopus85060937013
dc.identifier.isi000482589400025
dc.contributor.authorscopusid26435354100
dc.contributor.authorscopusid17434042000
dc.contributor.authorscopusid26421466600
dc.contributor.authorscopusid35092238600
dc.contributor.authorscopusid7003687617
dc.description.lastpage2885-
dc.description.firstpage2876-
dc.investigacionIngeniería y Arquitecturaen_US
dc.type2Artículoen_US
dc.contributor.daisngid7111180
dc.contributor.daisngid31454799
dc.contributor.daisngid1882101
dc.contributor.daisngid534244
dc.contributor.daisngid32553553
dc.utils.revisionen_US
dc.contributor.wosstandardWOS:Mellouli, D
dc.contributor.wosstandardWOS:Hamdani, TM
dc.contributor.wosstandardWOS:Sanchez-Medina, JJ
dc.contributor.wosstandardWOS:Ben Ayed, M
dc.contributor.wosstandardWOS:Mimi, AM
dc.date.coverdateSeptiembre 2019
dc.identifier.ulpgces
dc.description.sjr3,555
dc.description.jcr8,793
dc.description.sjrqQ1
dc.description.jcrqQ1
dc.description.scieSCIE
item.fulltextSin texto completo-
item.grantfulltextnone-
crisitem.author.deptGIR IUCES: Centro de Innovación para la Empresa, el Turismo, la Internacionalización y la Sostenibilidad-
crisitem.author.deptIU de Cibernética, Empresa y Sociedad (IUCES)-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.orcid0000-0003-2530-3182-
crisitem.author.parentorgIU de Cibernética, Empresa y Sociedad (IUCES)-
crisitem.author.fullNameSánchez Medina, Javier Jesús-
Colección:Artículos
Vista resumida

Citas SCOPUSTM   

57
actualizado el 24-mar-2024

Citas de WEB OF SCIENCETM
Citations

49
actualizado el 25-feb-2024

Visitas

168
actualizado el 09-mar-2024

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.