Sistemas híbridos neuro-simbólicos: Una revisión

Guardado en:
Detalles Bibliográficos
Autor principal: Juan M. Corchado
Formato: Artículo científico
Lenguaje:en
Publicado: Asociación Española para la Inteligencia Artificial 2000
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866815747846569984
author Juan M. Corchado
author_facet Juan M. Corchado
contents Sistemas híbridos neuro-simbólicos: Una revisión Juan M. Corchado Florentino Fdez Riverola Ingeniería boosting machine learning interval based literals time series classication A supervised classi_cation method for temporal series, even multivariate, is presented. It is based on boosting very simple classi_ers: clauses with one literal in the body. The background predicates are based on temporal intervals. Two types of predicates are used: i) relative predicates, such as \increases" and \stays", and ii) region predicates, such as \always" and \sometime", which operate over regions in the dominion of the variable. Experiments on di_erent data sets, several of them obtained from the UCI repositories, show that the proposed method is highly competitive with previous approaches 2000 artículo científico 1137-3601 https://www.redalyc.org/articulo.oa?id=92541102 en http://www.redalyc.org/revista.oa?id=925 Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial application/pdf Asociación Española para la Inteligencia Artificial Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial (España) Num.11 Vol.4
format Artículo científico
id redalyc_92541102
language en
publishDate 2000
publisher Asociación Española para la Inteligencia Artificial
spellingShingle Sistemas híbridos neuro-simbólicos: Una revisión
Juan M. Corchado
Ingeniería
boosting
machine learning
interval based literals
time series classication
Sistemas híbridos neuro-simbólicos: Una revisión Juan M. Corchado Florentino Fdez Riverola Ingeniería boosting machine learning interval based literals time series classication A supervised classi_cation method for temporal series, even multivariate, is presented. It is based on boosting very simple classi_ers: clauses with one literal in the body. The background predicates are based on temporal intervals. Two types of predicates are used: i) relative predicates, such as \increases" and \stays", and ii) region predicates, such as \always" and \sometime", which operate over regions in the dominion of the variable. Experiments on di_erent data sets, several of them obtained from the UCI repositories, show that the proposed method is highly competitive with previous approaches 2000 artículo científico 1137-3601 https://www.redalyc.org/articulo.oa?id=92541102 en http://www.redalyc.org/revista.oa?id=925 Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial application/pdf Asociación Española para la Inteligencia Artificial Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial (España) Num.11 Vol.4
title Sistemas híbridos neuro-simbólicos: Una revisión
topic Ingeniería
boosting
machine learning
interval based literals
time series classication
url https://www.redalyc.org/articulo.oa?id=92541102