Global and partial function approximation with evolutionary algorithms

We present an evolutionary algorithm that evolves a population of local approximators in order to fit an unknown function. The evolutionary algorithm performs a simultaneous learning of simple local approximators together with the regions in which the local approximators are applied. By combining th...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kavka, Carlos, Roggero, Patricia, Schoenauer, Marc
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2001
Materias:
Ciencias Informáticas
Evolutionary computation
Voronoi diagrams
Neural nets
Algorithms
ARTIFICIAL INTELLIGENCE
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23402
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23402
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
Voronoi diagrams
Neural nets
Algorithms
ARTIFICIAL INTELLIGENCE
spellingShingle Ciencias Informáticas
Evolutionary computation
Voronoi diagrams
Neural nets
Algorithms
ARTIFICIAL INTELLIGENCE
Kavka, Carlos
Roggero, Patricia
Schoenauer, Marc
Global and partial function approximation with evolutionary algorithms
topic_facet Ciencias Informáticas
Evolutionary computation
Voronoi diagrams
Neural nets
Algorithms
ARTIFICIAL INTELLIGENCE
description We present an evolutionary algorithm that evolves a population of local approximators in order to fit an unknown function. The evolutionary algorithm performs a simultaneous learning of simple local approximators together with the regions in which the local approximators are applied. By combining these simple local approximators, the domain is in fact partitioned in the Voronoi diagram that has as centers, the center points of the region in which each local approximator is efficient and useful. Both continuous and non-continuous approaches are considered. The algorithm seems promising in order to develop good neural networks for function approximation.
format Objeto de conferencia
Objeto de conferencia
author Kavka, Carlos
Roggero, Patricia
Schoenauer, Marc
author_facet Kavka, Carlos
Roggero, Patricia
Schoenauer, Marc
author_sort Kavka, Carlos
title Global and partial function approximation with evolutionary algorithms
title_short Global and partial function approximation with evolutionary algorithms
title_full Global and partial function approximation with evolutionary algorithms
title_fullStr Global and partial function approximation with evolutionary algorithms
title_full_unstemmed Global and partial function approximation with evolutionary algorithms
title_sort global and partial function approximation with evolutionary algorithms
publishDate 2001
url http://sedici.unlp.edu.ar/handle/10915/23402
work_keys_str_mv AT kavkacarlos globalandpartialfunctionapproximationwithevolutionaryalgorithms
AT roggeropatricia globalandpartialfunctionapproximationwithevolutionaryalgorithms
AT schoenauermarc globalandpartialfunctionapproximationwithevolutionaryalgorithms
bdutipo_str Repositorios
_version_ 1764820465885380609

Ejemplares similares