Invariance and Same-Equivariance Measures for Convolutional Neural Networks

Autores
Quiroga, Facundo Manuel
Año de publicación
2020
Idioma
inglés
Tipo de recurso
reseña artículo
Estado
versión publicada
Descripción
Our main objective in this thesis is to contribute to the understanding and improvement of equivariance in neural network models. In terms of applications, we focus on handshape classification for sign language and other types of gestures using convolutional networks. Therefore, we set the following specific goals: • Analyze CNN models design specifically for equivariance • Compare specific models and data augmentation as means to obtain equivariance. Evaluate transfer learning strategies to obtain equivariant models starting with non-equivariant ones. • Develop equivariance measures for activations or inner representations in Neural Networks. Implement those measures in an open source library. Analyze the measures behavior, and compare with existing measures.
Facultad de Informática
Materia
Ciencias Informáticas
Neural networks
Convolutional Neural Networks
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/97204
Acceder
id SEDICI_6d87170754d645ed351fb953892217af
oai_identifier_str oai:sedici.unlp.edu.ar:10915/97204
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Invariance and Same-Equivariance Measures for Convolutional Neural NetworksQuiroga, Facundo ManuelCiencias InformáticasNeural networksConvolutional Neural NetworksOur main objective in this thesis is to contribute to the understanding and improvement of equivariance in neural network models. In terms of applications, we focus on handshape classification for sign language and other types of gestures using convolutional networks. Therefore, we set the following specific goals: • Analyze CNN models design specifically for equivariance • Compare specific models and data augmentation as means to obtain equivariance. Evaluate transfer learning strategies to obtain equivariant models starting with non-equivariant ones. • Develop equivariance measures for activations or inner representations in Neural Networks. Implement those measures in an open source library. Analyze the measures behavior, and compare with existing measures.Facultad de Informática2020-05info:eu-repo/semantics/reviewinfo:eu-repo/semantics/publishedVersionRevisionhttp://purl.org/coar/resource_type/c_dcae04bcinfo:ar-repo/semantics/resenaArticuloapplication/pdfhttp://sedici.unlp.edu.ar/handle/10915/97204enginfo:eu-repo/semantics/altIdentifier/issn/1666-6038info:eu-repo/semantics/altIdentifier/doi/10.24215/16666038.20.e06info:eu-repo/semantics/reference/hdl/10915/90903info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc/4.0/Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T11:20:55Zoai:sedici.unlp.edu.ar:10915/97204Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 11:20:55.55SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Invariance and Same-Equivariance Measures for Convolutional Neural Networks
title Invariance and Same-Equivariance Measures for Convolutional Neural Networks
spellingShingle Invariance and Same-Equivariance Measures for Convolutional Neural Networks
Quiroga, Facundo Manuel
Ciencias Informáticas
Neural networks
Convolutional Neural Networks
title_short Invariance and Same-Equivariance Measures for Convolutional Neural Networks
title_full Invariance and Same-Equivariance Measures for Convolutional Neural Networks
title_fullStr Invariance and Same-Equivariance Measures for Convolutional Neural Networks
title_full_unstemmed Invariance and Same-Equivariance Measures for Convolutional Neural Networks
title_sort Invariance and Same-Equivariance Measures for Convolutional Neural Networks
dc.creator.none.fl_str_mv Quiroga, Facundo Manuel
author Quiroga, Facundo Manuel
author_facet Quiroga, Facundo Manuel
author_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
Neural networks
Convolutional Neural Networks
topic Ciencias Informáticas
Neural networks
Convolutional Neural Networks
dc.description.none.fl_txt_mv Our main objective in this thesis is to contribute to the understanding and improvement of equivariance in neural network models. In terms of applications, we focus on handshape classification for sign language and other types of gestures using convolutional networks. Therefore, we set the following specific goals: • Analyze CNN models design specifically for equivariance • Compare specific models and data augmentation as means to obtain equivariance. Evaluate transfer learning strategies to obtain equivariant models starting with non-equivariant ones. • Develop equivariance measures for activations or inner representations in Neural Networks. Implement those measures in an open source library. Analyze the measures behavior, and compare with existing measures.
Facultad de Informática
description Our main objective in this thesis is to contribute to the understanding and improvement of equivariance in neural network models. In terms of applications, we focus on handshape classification for sign language and other types of gestures using convolutional networks. Therefore, we set the following specific goals: • Analyze CNN models design specifically for equivariance • Compare specific models and data augmentation as means to obtain equivariance. Evaluate transfer learning strategies to obtain equivariant models starting with non-equivariant ones. • Develop equivariance measures for activations or inner representations in Neural Networks. Implement those measures in an open source library. Analyze the measures behavior, and compare with existing measures.
publishDate 2020
dc.date.none.fl_str_mv 2020-05
dc.type.none.fl_str_mv info:eu-repo/semantics/review
info:eu-repo/semantics/publishedVersion
Revision
http://purl.org/coar/resource_type/c_dcae04bc
info:ar-repo/semantics/resenaArticulo
format review
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/97204
url http://sedici.unlp.edu.ar/handle/10915/97204
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/issn/1666-6038
info:eu-repo/semantics/altIdentifier/doi/10.24215/16666038.20.e06
info:eu-repo/semantics/reference/hdl/10915/90903
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc/4.0/
Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc/4.0/
Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844616084015022080
score 13.069144

Publicaciones similares