Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods
Autor(a) principal: | |
---|---|
Data de Publicação: | 2013 |
Outros Autores: | , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://hdl.handle.net/11449/196052 |
Resumo: | Artificial Neural Networks are widely used in various applications in engineering, as such solutions of nonlinear problems. The implementation of this technique in reconfigurable devices is a great challenge to researchers by several factors, such as floating point precision, nonlinear activation function, performance and area used in FPGA. The contribution of this work is the approximation of a nonlinear function used in ANN, the popular hyperbolic tangent activation function. The system architecture is composed of several scenarios that provide a tradeoff of performance, precision and area used in FPGA. The results are compared in different scenarios and with current literature on error analysis, area and system performance. |
id |
UNSP_6de569e5cc413e9dd7804941775075e0 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/196052 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methodshyperbolic tangentFPGAactivation functionHybrid MethodsArtificial Neural Networks are widely used in various applications in engineering, as such solutions of nonlinear problems. The implementation of this technique in reconfigurable devices is a great challenge to researchers by several factors, such as floating point precision, nonlinear activation function, performance and area used in FPGA. The contribution of this work is the approximation of a nonlinear function used in ANN, the popular hyperbolic tangent activation function. The system architecture is composed of several scenarios that provide a tradeoff of performance, precision and area used in FPGA. The results are compared in different scenarios and with current literature on error analysis, area and system performance.UNEMATUNESP and PPGEELPSSDCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)UNEMAT Univ Estado Mato Grosso, Dept Comp, Colider, MT, BrazilUniv Estadual Paulista, UNESP, Dept Elect Engn, Ilha Solteria, SP, BrazilUniv Estadual Paulista, UNESP, Dept Elect Engn, Ilha Solteria, SP, BrazilCNPq: 309023/2012-2IeeeUNEMAT Univ Estado Mato GrossoUniversidade Estadual Paulista (Unesp)Sartin, Maicon A.Silva, Alexandre C. R. da [UNESP]IEEE2020-12-10T19:31:42Z2020-12-10T19:31:42Z2013-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject62013 8th International Workshop On Reconfigurable And Communication-centric Systems-on-chip (recosoc). New York: Ieee, 6 p., 2013.http://hdl.handle.net/11449/196052WOS:000327312100029Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2013 8th International Workshop On Reconfigurable And Communication-centric Systems-on-chip (recosoc)info:eu-repo/semantics/openAccess2024-07-04T19:11:33Zoai:repositorio.unesp.br:11449/196052Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:38:11.440490Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods |
title |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods |
spellingShingle |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods Sartin, Maicon A. hyperbolic tangent FPGA activation function Hybrid Methods |
title_short |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods |
title_full |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods |
title_fullStr |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods |
title_full_unstemmed |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods |
title_sort |
Approximation of Hyperbolic Tangent Activation Function Using Hybrid Methods |
author |
Sartin, Maicon A. |
author_facet |
Sartin, Maicon A. Silva, Alexandre C. R. da [UNESP] IEEE |
author_role |
author |
author2 |
Silva, Alexandre C. R. da [UNESP] IEEE |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
UNEMAT Univ Estado Mato Grosso Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Sartin, Maicon A. Silva, Alexandre C. R. da [UNESP] IEEE |
dc.subject.por.fl_str_mv |
hyperbolic tangent FPGA activation function Hybrid Methods |
topic |
hyperbolic tangent FPGA activation function Hybrid Methods |
description |
Artificial Neural Networks are widely used in various applications in engineering, as such solutions of nonlinear problems. The implementation of this technique in reconfigurable devices is a great challenge to researchers by several factors, such as floating point precision, nonlinear activation function, performance and area used in FPGA. The contribution of this work is the approximation of a nonlinear function used in ANN, the popular hyperbolic tangent activation function. The system architecture is composed of several scenarios that provide a tradeoff of performance, precision and area used in FPGA. The results are compared in different scenarios and with current literature on error analysis, area and system performance. |
publishDate |
2013 |
dc.date.none.fl_str_mv |
2013-01-01 2020-12-10T19:31:42Z 2020-12-10T19:31:42Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
2013 8th International Workshop On Reconfigurable And Communication-centric Systems-on-chip (recosoc). New York: Ieee, 6 p., 2013. http://hdl.handle.net/11449/196052 WOS:000327312100029 |
identifier_str_mv |
2013 8th International Workshop On Reconfigurable And Communication-centric Systems-on-chip (recosoc). New York: Ieee, 6 p., 2013. WOS:000327312100029 |
url |
http://hdl.handle.net/11449/196052 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2013 8th International Workshop On Reconfigurable And Communication-centric Systems-on-chip (recosoc) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
6 |
dc.publisher.none.fl_str_mv |
Ieee |
publisher.none.fl_str_mv |
Ieee |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128837298421760 |