Minimum description length quality measurues for modular functional network architectures

Modular neural networks (MNNs) are increasingly popular models for dealing with complex problems constituted by a number of dependent subtasks. An important problem on MNNs is finding the optimal aggregation of the neural modules, each of them dealing with one of the subproblems. In this paper, we p...

Descripción completa

Detalles Bibliográficos
Autores principales: Cofiño, Antonio S., Gutiérrez, José Manuel, Ivanissevich, María Laura
Formato: Objeto de conferencia
Lenguaje:Español
Publicado: 2001
Materias:
Ciencias Informáticas
functional networks
modular systems
model selection methods
time series prediction
Neural nets
Architectures
ARTIFICIAL INTELLIGENCE
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23399
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23399
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Español
topic Ciencias Informáticas
functional networks
modular systems
model selection methods
time series prediction
Neural nets
Architectures
ARTIFICIAL INTELLIGENCE
spellingShingle Ciencias Informáticas
functional networks
modular systems
model selection methods
time series prediction
Neural nets
Architectures
ARTIFICIAL INTELLIGENCE
Cofiño, Antonio S.
Gutiérrez, José Manuel
Ivanissevich, María Laura
Minimum description length quality measurues for modular functional network architectures
topic_facet Ciencias Informáticas
functional networks
modular systems
model selection methods
time series prediction
Neural nets
Architectures
ARTIFICIAL INTELLIGENCE
description Modular neural networks (MNNs) are increasingly popular models for dealing with complex problems constituted by a number of dependent subtasks. An important problem on MNNs is finding the optimal aggregation of the neural modules, each of them dealing with one of the subproblems. In this paper, we present a functional network approach, based on the minimum description length quality measure, to the problem of finding optimal modular network architectures for specific problems. Examples of function approximation and nonlinear time series prediction are used to illustrate the performance of these models when compared with standard functional and neural networks.
format Objeto de conferencia
Objeto de conferencia
author Cofiño, Antonio S.
Gutiérrez, José Manuel
Ivanissevich, María Laura
author_facet Cofiño, Antonio S.
Gutiérrez, José Manuel
Ivanissevich, María Laura
author_sort Cofiño, Antonio S.
title Minimum description length quality measurues for modular functional network architectures
title_short Minimum description length quality measurues for modular functional network architectures
title_full Minimum description length quality measurues for modular functional network architectures
title_fullStr Minimum description length quality measurues for modular functional network architectures
title_full_unstemmed Minimum description length quality measurues for modular functional network architectures
title_sort minimum description length quality measurues for modular functional network architectures
publishDate 2001
url http://sedici.unlp.edu.ar/handle/10915/23399
work_keys_str_mv AT cofinoantonios minimumdescriptionlengthqualitymeasuruesformodularfunctionalnetworkarchitectures
AT gutierrezjosemanuel minimumdescriptionlengthqualitymeasuruesformodularfunctionalnetworkarchitectures
AT ivanissevichmarialaura minimumdescriptionlengthqualitymeasuruesformodularfunctionalnetworkarchitectures
bdutipo_str Repositorios
_version_ 1764820465881186308

Ejemplares similares