Optimizing the Simplicial-Map Neural Network Architecture

Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined to be robust to adversarial attacks. In this paper,...

Descripción completa

Detalles Bibliográficos
Autores: Paluzo Hidalgo, Eduardo, González Díaz, Rocío, Gutiérrez Naranjo, Miguel Ángel, Heras, Jónathan
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/126693
Acceso en línea:https://hdl.handle.net/11441/126693
https://doi.org/10.3390/jimaging7090173
Access Level:acceso abierto
Palabra clave:Simplicial-map neural networks
Artificial neural networks
Computational topology
id ES_35ce715f8a846eeaafa7cc4135b1dfa1
oai_identifier_str oai:idus.us.es:11441/126693
network_acronym_str ES
network_name_str España
repository_id_str
spelling Optimizing the Simplicial-Map Neural Network ArchitecturePaluzo Hidalgo, EduardoGonzález Díaz, RocíoGutiérrez Naranjo, Miguel ÁngelHeras, JónathanSimplicial-map neural networksArtificial neural networksComputational topologySimplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined to be robust to adversarial attacks. In this paper, the refinement toward robustness is optimized by reducing the number of simplices (i.e., nodes) needed. We have shown experimentally that such a refined neural network is equivalent to the original network as a classification tool but requires much less storage.Agencia Estatal de Investigación PID2019-107339GB-100MDPIMatemática Aplicada ICiencias de la Computación e Inteligencia ArtificialAgencia Estatal de Investigación. España2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/126693https://doi.org/10.3390/jimaging7090173reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésJournal of Imaging, 7 (9)PID2019- 107339GB-100https://www.mdpi.com/2313-433X/7/9/173info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1266932026-06-17T12:51:07Z
dc.title.none.fl_str_mv Optimizing the Simplicial-Map Neural Network Architecture
title Optimizing the Simplicial-Map Neural Network Architecture
spellingShingle Optimizing the Simplicial-Map Neural Network Architecture
Paluzo Hidalgo, Eduardo
Simplicial-map neural networks
Artificial neural networks
Computational topology
title_short Optimizing the Simplicial-Map Neural Network Architecture
title_full Optimizing the Simplicial-Map Neural Network Architecture
title_fullStr Optimizing the Simplicial-Map Neural Network Architecture
title_full_unstemmed Optimizing the Simplicial-Map Neural Network Architecture
title_sort Optimizing the Simplicial-Map Neural Network Architecture
dc.creator.none.fl_str_mv Paluzo Hidalgo, Eduardo
González Díaz, Rocío
Gutiérrez Naranjo, Miguel Ángel
Heras, Jónathan
author Paluzo Hidalgo, Eduardo
author_facet Paluzo Hidalgo, Eduardo
González Díaz, Rocío
Gutiérrez Naranjo, Miguel Ángel
Heras, Jónathan
author_role author
author2 González Díaz, Rocío
Gutiérrez Naranjo, Miguel Ángel
Heras, Jónathan
author2_role author
author
author
dc.contributor.none.fl_str_mv Matemática Aplicada I
Ciencias de la Computación e Inteligencia Artificial
Agencia Estatal de Investigación. España
dc.subject.none.fl_str_mv Simplicial-map neural networks
Artificial neural networks
Computational topology
topic Simplicial-map neural networks
Artificial neural networks
Computational topology
description Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined to be robust to adversarial attacks. In this paper, the refinement toward robustness is optimized by reducing the number of simplices (i.e., nodes) needed. We have shown experimentally that such a refined neural network is equivalent to the original network as a classification tool but requires much less storage.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/126693
https://doi.org/10.3390/jimaging7090173
url https://hdl.handle.net/11441/126693
https://doi.org/10.3390/jimaging7090173
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Journal of Imaging, 7 (9)
PID2019- 107339GB-100
https://www.mdpi.com/2313-433X/7/9/173
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405912105484288
score 15,300719

Similares en LA Referencia