A parallel approach for backpropagation learning of neural networks

Learning algorithms for neural networks involve CPU intensive processing and consequently great effort has been done to develop parallel implemetations intended for a reduction of learning time. This work briefly describes parallel schemes for a backpropagation algorithm and proposes a distributed...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Crespo, María Liz, Piccoli, María Fabiana, Printista, Alicia Marcela, Gallard, Raúl Hector
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 1997
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23892
Aporte de:
id I19-R120-10915-23892
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
Neutral networks
parallelised backpropagation
partitioning schemes
pattern partitioning
system architecture
Architectures
Parallel
Neural nets
Distributed
spellingShingle Ciencias Informáticas
Neutral networks
parallelised backpropagation
partitioning schemes
pattern partitioning
system architecture
Architectures
Parallel
Neural nets
Distributed
Crespo, María Liz
Piccoli, María Fabiana
Printista, Alicia Marcela
Gallard, Raúl Hector
A parallel approach for backpropagation learning of neural networks
topic_facet Ciencias Informáticas
Neutral networks
parallelised backpropagation
partitioning schemes
pattern partitioning
system architecture
Architectures
Parallel
Neural nets
Distributed
description Learning algorithms for neural networks involve CPU intensive processing and consequently great effort has been done to develop parallel implemetations intended for a reduction of learning time. This work briefly describes parallel schemes for a backpropagation algorithm and proposes a distributed system architecture for developing parallel training with a partition pattern scheme. Under this approach, weight changes are computed concurrently, exchanged between system components and adjusted accordingly until the whole parallel learning process is completed. Some comparative results are also shown.
format Objeto de conferencia
Objeto de conferencia
author Crespo, María Liz
Piccoli, María Fabiana
Printista, Alicia Marcela
Gallard, Raúl Hector
author_facet Crespo, María Liz
Piccoli, María Fabiana
Printista, Alicia Marcela
Gallard, Raúl Hector
author_sort Crespo, María Liz
title A parallel approach for backpropagation learning of neural networks
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 parallel approach for backpropagation learning of neural networks
publishDate 1997
url http://sedici.unlp.edu.ar/handle/10915/23892
work_keys_str_mv AT crespomarializ aparallelapproachforbackpropagationlearningofneuralnetworks
AT piccolimariafabiana aparallelapproachforbackpropagationlearningofneuralnetworks
AT printistaaliciamarcela aparallelapproachforbackpropagationlearningofneuralnetworks
AT gallardraulhector aparallelapproachforbackpropagationlearningofneuralnetworks
AT crespomarializ parallelapproachforbackpropagationlearningofneuralnetworks
AT piccolimariafabiana parallelapproachforbackpropagationlearningofneuralnetworks
AT printistaaliciamarcela parallelapproachforbackpropagationlearningofneuralnetworks
AT gallardraulhector parallelapproachforbackpropagationlearningofneuralnetworks
bdutipo_str Repositorios
_version_ 1764820466377162752