Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm

"Learning the bayesian network structure from a database is an NP-Hard problem for which the existent learning algorithms generally have exponential complexity. During this work in the Master, I did a bibliographic research as well as a comparison between two recent algorithms called TPDA and P...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Groppo Parisi, Tomás
Otros Autores: Aussem, Alexandre
Formato: Proyecto final de Grado
Lenguaje:Español
Publicado: 2020
Materias:
REDES BAYESIANAS
ALGORITMOS
MINERIA DE DATOS
Acceso en línea:http://ri.itba.edu.ar/handle/123456789/3098
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-123456789-3098
record_format dspace
spelling I32-R138-123456789-30982022-12-07T14:28:59Z Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm Groppo Parisi, Tomás Aussem, Alexandre REDES BAYESIANAS ALGORITMOS MINERIA DE DATOS "Learning the bayesian network structure from a database is an NP-Hard problem for which the existent learning algorithms generally have exponential complexity. During this work in the Master, I did a bibliographic research as well as a comparison between two recent algorithms called TPDA and PMMS (2005) that learns the skeleton of bayesian networks from data. These algorithms have the advantage of having polynomial complexity, and provide good results for learning. After having done a theoretical analysis of the algorithms, I continue with an empiric analysis that consisted in testing these algorithms on data generated from networks knew by the scientific community (I used ASIA and ALARM networks). These tests have been made with the help of the toolboxes developed in Matlab (FullBNT, BNT – SLP and CausalExplorer). The results I have gotten by this analysis have permitted me to make some interesting conclusions about the efficiency and the limits of application of these algorithms." "El aprendizaje del esqueleto de una red bayesiana a partir de una base de datos es un problema NP-Dificil para el cual los algoritmos de aprendizaje existentes son generalmente de complejidad exponencial. En el transcurso de la pasantía del Master, he efectuado una investigación bibliográfica así como una comparación entre dos algoritmos recientes de aprendizaje del esqueleto de las redes bayesianas. Ellos son TPDA y PMMS (2005). Estos algoritmos tienen la ventaja de tener una complejidad polinomial y proveen buenos resultados de aprendizaje. Luego de haber efectuado un análisis teórico de los algoritmos, he continuado con un análisis empírico. Este consistió en testear estos algoritmos sobre datos generados a partir de redes conocidas por la comunidad científica (he utilizado la red ASIA y ALARM). Esto fue realizado con la ayuda de las cajas de herramientas desarrolladas en Matlab (FullBNT , BNT – SLP y CausalExplorer). Los resultados obtenidos por este análisis me permitieron formular conclusiones interesantes en cuanto a la eficacia y a los límites de aplicación de estos algoritmos." Proyecto final Ingeniería Industrial (grado) - Instituto Tecnológico de Buenos Aires, Buenos Aires, 2006 2020-09-29T14:45:48Z 2020-09-29T14:45:48Z 2006 Proyecto final de Grado http://ri.itba.edu.ar/handle/123456789/3098 es application/pdf
institution Instituto Tecnológico de Buenos Aires (ITBA)
institution_str I-32
repository_str R-138
collection Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA)
language Español
topic REDES BAYESIANAS
ALGORITMOS
MINERIA DE DATOS
spellingShingle REDES BAYESIANAS
ALGORITMOS
MINERIA DE DATOS
Groppo Parisi, Tomás
Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm
topic_facet REDES BAYESIANAS
ALGORITMOS
MINERIA DE DATOS
description "Learning the bayesian network structure from a database is an NP-Hard problem for which the existent learning algorithms generally have exponential complexity. During this work in the Master, I did a bibliographic research as well as a comparison between two recent algorithms called TPDA and PMMS (2005) that learns the skeleton of bayesian networks from data. These algorithms have the advantage of having polynomial complexity, and provide good results for learning. After having done a theoretical analysis of the algorithms, I continue with an empiric analysis that consisted in testing these algorithms on data generated from networks knew by the scientific community (I used ASIA and ALARM networks). These tests have been made with the help of the toolboxes developed in Matlab (FullBNT, BNT – SLP and CausalExplorer). The results I have gotten by this analysis have permitted me to make some interesting conclusions about the efficiency and the limits of application of these algorithms."
author2 Aussem, Alexandre
author_facet Aussem, Alexandre
Groppo Parisi, Tomás
format Proyecto final de Grado
author Groppo Parisi, Tomás
author_sort Groppo Parisi, Tomás
title Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm
title_short Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm
title_full Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm
title_fullStr Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm
title_full_unstemmed Learning Bayesian networks skeleton: a comparison between TPDA and PMMS algorithm
title_sort learning bayesian networks skeleton: a comparison between tpda and pmms algorithm
publishDate 2020
url http://ri.itba.edu.ar/handle/123456789/3098
work_keys_str_mv AT groppoparisitomas learningbayesiannetworksskeletonacomparisonbetweentpdaandpmmsalgorithm
_version_ 1765661106293964800

Ejemplares similares