Random forest-like strategies for neural networks ensembles contruction

Ensemble methods show improved generalization capabilities that outperforrn those of single larners. lt is generally accepted that, for aggregation to be effective, the individual learners must be as accurate and diverse as possible. An important problem in ensemble learning is then how to find a go...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Namías, Rafael, Granitto, Pablo Miguel
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2007
Materias:
Ciencias Informáticas
Informática
Neural nets
Network communications
Network management
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23485
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23485
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
Informática
Neural nets
Network communications
Network management
spellingShingle Ciencias Informáticas
Informática
Neural nets
Network communications
Network management
Namías, Rafael
Granitto, Pablo Miguel
Random forest-like strategies for neural networks ensembles contruction
topic_facet Ciencias Informáticas
Informática
Neural nets
Network communications
Network management
description Ensemble methods show improved generalization capabilities that outperforrn those of single larners. lt is generally accepted that, for aggregation to be effective, the individual learners must be as accurate and diverse as possible. An important problem in ensemble learning is then how to find a good balance between these two conflicting conditions. For tree-based methods a successfill strategy was introduced by Breiman with the Random-Forest algorithm. In this work we introduce new methods for neural network ensemble construction that follow Random-Forest-like strategies to construct ensembles. Using several real and artificial regression problems, we compare onr new methods with the more typical Bagging algorithrm and with three state-of-the-art regression methods. We find that our algorithms produce very good results on several datasets. Some evidence suggest that our new methods work better on problems with several redundant or noisy inputs.
format Objeto de conferencia
Objeto de conferencia
author Namías, Rafael
Granitto, Pablo Miguel
author_facet Namías, Rafael
Granitto, Pablo Miguel
author_sort Namías, Rafael
title Random forest-like strategies for neural networks ensembles contruction
title_short Random forest-like strategies for neural networks ensembles contruction
title_full Random forest-like strategies for neural networks ensembles contruction
title_fullStr Random forest-like strategies for neural networks ensembles contruction
title_full_unstemmed Random forest-like strategies for neural networks ensembles contruction
title_sort random forest-like strategies for neural networks ensembles contruction
publishDate 2007
url http://sedici.unlp.edu.ar/handle/10915/23485
work_keys_str_mv AT namiasrafael randomforestlikestrategiesforneuralnetworksensemblescontruction
AT granittopablomiguel randomforestlikestrategiesforneuralnetworksensemblescontruction
bdutipo_str Repositorios
_version_ 1764820466020646914

Ejemplares similares