A parallel approach for backpropagation learning of neural networks

Fast response, storage efficiency, fault tolerance and graceful degradation in face of scarce or spurious inputs make neural networks appropiate tools for Intelligent Computer Systems. But on the other hand, learning algorithms for neural networks involve CPU intensive processing and consequently gr...

Descripción completa

Detalles Bibliográficos
Autores: Crespo, María Liz, Piccoli, María Fabiana, Printista, Alicia Marcela, Gallard, Raúl Hector
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:1999
País:Argentina
Institución:Universidad Nacional de La Plata
Repositorio:SEDICI (UNLP)
Idioma:inglés
OAI Identifier:oai:sedici.unlp.edu.ar:10915/9378
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/9378
Access Level:acceso abierto
Palabra clave:Ciencias Informáticas
Neural nets
id AR_4d77abded2d33cf0b517d39ce2ec6ab7
oai_identifier_str oai:sedici.unlp.edu.ar:10915/9378
network_acronym_str AR
network_name_str Argentina
repository_id_str
spelling A parallel approach for backpropagation learning of neural networksCrespo, María LizPiccoli, María FabianaPrintista, Alicia MarcelaGallard, Raúl HectorCiencias InformáticasNeural netsFast response, storage efficiency, fault tolerance and graceful degradation in face of scarce or spurious inputs make neural networks appropiate tools for Intelligent Computer Systems. But on the other hand, learning algorithms for neural networks involve CPU intensive processing and consequently great effort hass been done to develop parallel implementation intended for a reduction of learning time. Looking at both sides of the coin, this paper shows firstly two alternatives to parallelise the learning process and then an apllication of neural networks to computing systems. On the parallel alternative distributed implementations to parallelise the learning process of neural networks using pattern partitioning approach. Under this approach weight changes are computed concurently, exchanged between system components and adjusted accordingly until the whole parallel learning process is completed. On the application side, some design and implementation insights to build a system where decision support for load distribution is based on a neural network device are shown. Incoming task allocation, as a previous step, is a fundamental service aiming for improving distributed system perfomance facilitating further dynamic load balancing. A neural network device inserted into the kernel of a distributed system as an intelligent dool, allows to achieve automatic allocation of execution requests under some predefinided perfomance criteria based on resource availability and incoming process requeriments. Perfomamnec results of the parallelised approach for learning of backpropagation neural networks, are shown. This include a comparison of recall and generalisation abilities to support parallelism.Facultad de Informática1999-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArticulohttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttp://sedici.unlp.edu.ar/handle/10915/9378enginfo:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/wp-content/uploads/2015/papers_01/a%20parallel.pdfinfo:eu-repo/semantics/altIdentifier/issn/1666-6038info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc/3.0/Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2024-05-08T12:30:00Zoai:sedici.unlp.edu.ar:10915/9378Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292024-05-08 12:30:00.705SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv A parallel approach for backpropagation learning of neural networks
title A parallel approach for backpropagation learning of neural networks
spellingShingle A parallel approach for backpropagation learning of neural networks
Crespo, María Liz
Ciencias Informáticas
Neural nets
title_short A parallel approach for backpropagation learning of neural networks
title_full A parallel approach for backpropagation learning of neural networks
title_fullStr A parallel approach for backpropagation learning of neural networks
title_full_unstemmed A parallel approach for backpropagation learning of neural networks
title_sort A parallel approach for backpropagation learning of neural networks
dc.creator.none.fl_str_mv Crespo, María Liz
Piccoli, María Fabiana
Printista, Alicia Marcela
Gallard, Raúl Hector
author Crespo, María Liz
author_facet Crespo, María Liz
Piccoli, María Fabiana
Printista, Alicia Marcela
Gallard, Raúl Hector
author_role author
author2 Piccoli, María Fabiana
Printista, Alicia Marcela
Gallard, Raúl Hector
author2_role author
author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Neural nets
topic Ciencias Informáticas
Neural nets
description Fast response, storage efficiency, fault tolerance and graceful degradation in face of scarce or spurious inputs make neural networks appropiate tools for Intelligent Computer Systems. But on the other hand, learning algorithms for neural networks involve CPU intensive processing and consequently great effort hass been done to develop parallel implementation intended for a reduction of learning time. Looking at both sides of the coin, this paper shows firstly two alternatives to parallelise the learning process and then an apllication of neural networks to computing systems. On the parallel alternative distributed implementations to parallelise the learning process of neural networks using pattern partitioning approach. Under this approach weight changes are computed concurently, exchanged between system components and adjusted accordingly until the whole parallel learning process is completed. On the application side, some design and implementation insights to build a system where decision support for load distribution is based on a neural network device are shown. Incoming task allocation, as a previous step, is a fundamental service aiming for improving distributed system perfomance facilitating further dynamic load balancing. A neural network device inserted into the kernel of a distributed system as an intelligent dool, allows to achieve automatic allocation of execution requests under some predefinided perfomance criteria based on resource availability and incoming process requeriments. Perfomamnec results of the parallelised approach for learning of backpropagation neural networks, are shown. This include a comparison of recall and generalisation abilities to support parallelism.
publishDate 1999
dc.date.none.fl_str_mv 1999-03
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Articulo
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/9378
url http://sedici.unlp.edu.ar/handle/10915/9378
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/wp-content/uploads/2015/papers_01/a%20parallel.pdf
info:eu-repo/semantics/altIdentifier/issn/1666-6038
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc/3.0/
Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc/3.0/
Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)
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
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1799193961944842240
score 15.812429

Similares en LA Referencia