Mostrar el registro sencillo del ítem

dc.contributor.authorRodríguez Martínez, Iosu
dc.contributor.authorHerrera Triguero, Francisco 
dc.date.accessioned2022-06-28T07:53:59Z
dc.date.available2022-06-28T07:53:59Z
dc.date.issued2022-05-06
dc.identifier.citationIosu Rodriguez-Martinez... [et al.]. Replacing pooling functions in Convolutional Neural Networks by linear combinations of increasing functions, Neural Networks, Volume 152, 2022, Pages 380-393, ISSN 0893-6080, [https://doi.org/10.1016/j.neunet.2022.04.028]es_ES
dc.identifier.urihttp://hdl.handle.net/10481/75689
dc.description.abstractTraditionally, Convolutional Neural Networks make use of the maximum or arithmetic mean in order to reduce the features extracted by convolutional layers in a downsampling process known as pooling. However, there is no strong argument to settle upon one of the two functions and, in practice, this selection turns to be problem dependent. Further, both of these options ignore possible dependencies among the data. We believe that a combination of both of these functions, as well as of additional ones which may retain different information, can benefit the feature extraction process. In this work, we replace traditional pooling by several alternative functions. In particular, we consider linear combinations of order statistics and generalizations of the Sugeno integral, extending the latter’s domain to the whole real line and setting the theoretical base for their application. We present an alternative pooling layer based on this strategy which we name ‘‘CombPool’’ layer. We replace the pooling layers of three different architectures of increasing complexity by CombPool layers, and empirically prove over multiple datasets that linear combinations outperform traditional pooling functions in most cases. Further, combinations with either the Sugeno integral or one of its generalizations usually yield the best results, proving a strong candidate to apply in most architectures.es_ES
dc.description.sponsorshipTracasa Instrumental (iTRACASA), Spaines_ES
dc.description.sponsorshipGobierno de Navarra-Departamento de Universidad, Innovacion y Transformacion Digital, Spaines_ES
dc.description.sponsorshipSpanish Ministry of Science, Spain PID2019-108392GB-I00es_ES
dc.description.sponsorshipAndalusian Excellence project, Spain PID2019-108392GB-I00es_ES
dc.description.sponsorshipConselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPQ) PC095-096es_ES
dc.description.sponsorshipFundacao de Amparo a Ciencia e Tecnologia do Estado do Rio Grande do Sul (FAPERGS) P18-FR-4961 301618/2019-4 19/2551-000 1279-9es_ES
dc.language.isoenges_ES
dc.publisherElsevieres_ES
dc.rightsAtribución 3.0 España*
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subjectConvolutional Neural Networkses_ES
dc.subjectPooling functiones_ES
dc.subjectOrder statistices_ES
dc.subjectGeneralized Sugeno integrales_ES
dc.titleReplacing pooling functions in Convolutional Neural Networks by linear combinations of increasing functionses_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses_ES
dc.identifier.doi10.1016/j.neunet.2022.04.028
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersiones_ES


Ficheros en el ítem

[PDF]

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

Mostrar el registro sencillo del ítem

Atribución 3.0 España
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución 3.0 España