Invariance and Same-Equivariance Measures for Convolutional Neural Networks

Mostrar todas las versiones(2)

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 followi...

Descripción completa

Detalles Bibliográficos
Autor principal: Quiroga, Facundo Manuel
Formato: Articulo Revision
Lenguaje:Inglés
Publicado: 2020
Materias:
Ciencias Informáticas
Neural networks
Convolutional Neural Networks
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/97204
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-97204
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Neural networks
Convolutional Neural Networks
spellingShingle Ciencias Informáticas
Neural networks
Convolutional Neural Networks
Quiroga, Facundo Manuel
Invariance and Same-Equivariance Measures for Convolutional Neural Networks
topic_facet Ciencias Informáticas
Neural networks
Convolutional Neural Networks
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.
format Articulo
Revision
author Quiroga, Facundo Manuel
author_facet Quiroga, Facundo Manuel
author_sort Quiroga, Facundo Manuel
title Invariance and Same-Equivariance Measures for 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
publishDate 2020
url http://sedici.unlp.edu.ar/handle/10915/97204
work_keys_str_mv AT quirogafacundomanuel invarianceandsameequivariancemeasuresforconvolutionalneuralnetworks
bdutipo_str Repositorios
_version_ 1764820492454199296

Ejemplares similares