Learning low inference complexity Bayesian networks

Benjumeda Barquita, Marco Alberto and Larrañaga Múgica, Pedro María and Bielza Lozoya, María Concepción (2015). Learning low inference complexity Bayesian networks. In: "XVI Conferencia de la Asociación Española para la Inteligencia Artificial (CAEPIA 2015)", 09-12 Nov 2015, Albacete, España. ISBN 978-84-608-4099-2. pp. 11-20.

Description

Title: Learning low inference complexity Bayesian networks
Author/s:
  • Benjumeda Barquita, Marco Alberto
  • Larrañaga Múgica, Pedro María
  • Bielza Lozoya, María Concepción
Item Type: Presentation at Congress or Conference (Other)
Event Title: XVI Conferencia de la Asociación Española para la Inteligencia Artificial (CAEPIA 2015)
Event Dates: 09-12 Nov 2015
Event Location: Albacete, España
Title of Book: Actas de la XVI Conferencia de la Asociación Española para la Inteligencia Artificial
Date: 2015
ISBN: 978-84-608-4099-2
Volume: 1
Subjects:
Freetext Keywords: Probabilistic graphical models; Bayesian networks; Arith- metic circuits; Network polynomials; Structure learning; Thin models
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (301kB) | Preview

Abstract

One of the main research topics in machine learning nowa- days is the improvement of the inference and learning processes in proba- bilistic graphical models. Traditionally, inference and learning have been treated separately, but given that the structure of the model conditions the inference complexity, most learning methods will sometimes produce ineficient inference models. In this paper we propose a new representa- tion for discrete probability distributions that allows eficiently evaluat- ing the inference complexity of the models during the learning process. We use this representation to create procedures for learning low infer- ence complexity Bayesian networks. Experimental results show that the proposed methods obtain tractable models that improve the accuracy of the predictions provided by approximate inference in models obtained with a well-known Bayesian network learner.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainC080020-09UnspecifiedUnspecifiedUnspecified
Madrid Regional GovernmentS2013/ICE-2845-CASI-CAM-CMUnspecifiedUnspecifiedUnspecified
FP7FP7/2007-2013UnspecifiedUnspecifiedUnspecified

More information

Item ID: 42133
DC Identifier: http://oa.upm.es/42133/
OAI Identifier: oai:oa.upm.es:42133
Official URL: http://simd.albacete.org/actascaepia15/
Deposited by: Memoria Investigacion
Deposited on: 20 Oct 2016 09:00
Last Modified: 20 Oct 2016 09:00
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM