Automatic Generation of Neural Networks

This work deals with methods for finding optimal neural network architectures to learn par-ticular problems. A genetic algorithm is used to discover suitable domain specific architectures; this evolutionary algorithm applies direct codification and uses the error from the trained network as a per-fo...

Descripción completa

Detalles Bibliográficos
Autores principales: Fiszelew, A., Britos, Paola Verónica, Perichinsky, Gregorio, García Martínez, Ramón
Formato: Articulo
Lenguaje:Inglés
Publicado: 2003
Materias:
Ciencias Informáticas
Evolutionary computation
Neural networks
Genetic algorithms
Codification methods
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/136295
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-136295
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
Evolutionary computation
Neural networks
Genetic algorithms
Codification methods
spellingShingle Ciencias Informáticas
Evolutionary computation
Neural networks
Genetic algorithms
Codification methods
Fiszelew, A.
Britos, Paola Verónica
Perichinsky, Gregorio
García Martínez, Ramón
Automatic Generation of Neural Networks
topic_facet Ciencias Informáticas
Evolutionary computation
Neural networks
Genetic algorithms
Codification methods
description This work deals with methods for finding optimal neural network architectures to learn par-ticular problems. A genetic algorithm is used to discover suitable domain specific architectures; this evolutionary algorithm applies direct codification and uses the error from the trained network as a per-formance measure to guide the evolution. The network training is accomplished by the back-propagation algorithm; techniques such as training repetition, early stopping and complex regulation are employed to improve the evolutionary process results. The evaluation criteria are based on learn-ing skills and classification accuracy of generated architectures.
format Articulo
Articulo
author Fiszelew, A.
Britos, Paola Verónica
Perichinsky, Gregorio
García Martínez, Ramón
author_facet Fiszelew, A.
Britos, Paola Verónica
Perichinsky, Gregorio
García Martínez, Ramón
author_sort Fiszelew, A.
title Automatic Generation of Neural Networks
title_short Automatic Generation of Neural Networks
title_full Automatic Generation of Neural Networks
title_fullStr Automatic Generation of Neural Networks
title_full_unstemmed Automatic Generation of Neural Networks
title_sort automatic generation of neural networks
publishDate 2003
url http://sedici.unlp.edu.ar/handle/10915/136295
work_keys_str_mv AT fiszelewa automaticgenerationofneuralnetworks
AT britospaolaveronica automaticgenerationofneuralnetworks
AT perichinskygregorio automaticgenerationofneuralnetworks
AT garciamartinezramon automaticgenerationofneuralnetworks
bdutipo_str Repositorios
_version_ 1764820456637988864

Ejemplares similares