Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions
Main Author: | |
---|---|
Publication Date: | 2012 |
Other Authors: | |
Format: | Article |
Language: | eng |
Source: | Repositório Institucional da Udesc |
dARK ID: | ark:/33523/001300000sgtr |
Download full: | https://repositorio.udesc.br/handle/UDESC/9156 |
Summary: | This paper reports two-dimensional parameter-space plots for both, the hyperbolic tangent and the piecewise-linear neuron activation functions of a three-dimensional Hopfield neural network. The plots obtained using both neuron activation functions are compared, and we show that similar features are present on them. The occurrence of self-organized periodic structures embedded in chaotic regions is verified for the two cases. © 2012 Elsevier Ltd. |
id |
UDESC-2_496760d3e9e94758c1318f980c2d4f75 |
---|---|
oai_identifier_str |
oai:repositorio.udesc.br:UDESC/9156 |
network_acronym_str |
UDESC-2 |
network_name_str |
Repositório Institucional da Udesc |
repository_id_str |
6391 |
spelling |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functionsThis paper reports two-dimensional parameter-space plots for both, the hyperbolic tangent and the piecewise-linear neuron activation functions of a three-dimensional Hopfield neural network. The plots obtained using both neuron activation functions are compared, and we show that similar features are present on them. The occurrence of self-organized periodic structures embedded in chaotic regions is verified for the two cases. © 2012 Elsevier Ltd.2024-12-06T19:06:01Z2012info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlep. 42 - 451879-278210.1016/j.neunet.2012.06.006https://repositorio.udesc.br/handle/UDESC/9156ark:/33523/001300000sgtrNeural Networks34Mathias A.C.*Rech P.C.*engreponame:Repositório Institucional da Udescinstname:Universidade do Estado de Santa Catarina (UDESC)instacron:UDESCinfo:eu-repo/semantics/openAccess2024-12-07T21:01:10Zoai:repositorio.udesc.br:UDESC/9156Biblioteca Digital de Teses e Dissertaçõeshttps://pergamumweb.udesc.br/biblioteca/index.phpPRIhttps://repositorio-api.udesc.br/server/oai/requestri@udesc.bropendoar:63912024-12-07T21:01:10Repositório Institucional da Udesc - Universidade do Estado de Santa Catarina (UDESC)false |
dc.title.none.fl_str_mv |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions |
title |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions |
spellingShingle |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions Mathias A.C.* |
title_short |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions |
title_full |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions |
title_fullStr |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions |
title_full_unstemmed |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions |
title_sort |
Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions |
author |
Mathias A.C.* |
author_facet |
Mathias A.C.* Rech P.C.* |
author_role |
author |
author2 |
Rech P.C.* |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Mathias A.C.* Rech P.C.* |
description |
This paper reports two-dimensional parameter-space plots for both, the hyperbolic tangent and the piecewise-linear neuron activation functions of a three-dimensional Hopfield neural network. The plots obtained using both neuron activation functions are compared, and we show that similar features are present on them. The occurrence of self-organized periodic structures embedded in chaotic regions is verified for the two cases. © 2012 Elsevier Ltd. |
publishDate |
2012 |
dc.date.none.fl_str_mv |
2012 2024-12-06T19:06:01Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
1879-2782 10.1016/j.neunet.2012.06.006 https://repositorio.udesc.br/handle/UDESC/9156 |
dc.identifier.dark.fl_str_mv |
ark:/33523/001300000sgtr |
identifier_str_mv |
1879-2782 10.1016/j.neunet.2012.06.006 ark:/33523/001300000sgtr |
url |
https://repositorio.udesc.br/handle/UDESC/9156 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Neural Networks 34 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
p. 42 - 45 |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da Udesc instname:Universidade do Estado de Santa Catarina (UDESC) instacron:UDESC |
instname_str |
Universidade do Estado de Santa Catarina (UDESC) |
instacron_str |
UDESC |
institution |
UDESC |
reponame_str |
Repositório Institucional da Udesc |
collection |
Repositório Institucional da Udesc |
repository.name.fl_str_mv |
Repositório Institucional da Udesc - Universidade do Estado de Santa Catarina (UDESC) |
repository.mail.fl_str_mv |
ri@udesc.br |
_version_ |
1842258169759268864 |