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
- Institución
- Universidad Nacional de La Plata
- OAI Identificador
- oai:sedici.unlp.edu.ar:10915/97204
Ver los metadatos del registro completo
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:UNLP2025-09-03T10:53:06Zoai: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:13292025-09-03 10:53:06.638SEDICI (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_ |
1842260413959372800 |
score |
13.13397 |