Welcome Guest!

Quick Find:  

Advanced Search

Languages: English Español

Valid XHTML 1.0 Transitional ¡CSS Válido! Icono de conformidad con el Nivel Doble-A, 
	de las Directrices de Accesibilidad para el 
	Contenido Web 1.0 del W3C-WAI

Improved Algorithms for Learning Bayesian Network Classifiers


Improved Algorithms for Learning Bayesian Network Classifiers
Improved Algorithms for Learning Bayesian Network Classifiers

Jesús Cerquides

Affiliation: Consejo Superior de Investigaciones Científicas. Institut d'Investigació en Intel-ligencia Artificial (Bellaterra, España)

Biography: Not available

Close window

Jesús Cerquides

About the authors 

Publication year: 2005

Language: English

Subjects: Science and Technology

Collection: Monografies de l'Institut d'Investigació en Intel-ligencia Artificial

Free eBook

Abstract:

This thesis applies objective Bayesian probability theory techniques to improve Bayesian network classifiers. The main contributions are: ─ A parallelizable distance based discretization method that allows to extend discrete classifiers to non-discrete domains. ─ The concepts of qualitative influences and synergies, which allow to improve understandability of Bayesian network classifiers. ─ The first order and second order qualitative Bayesian classifiers, which are classifiers based on qualitative influences and synergies, with easily understandable results and with a reasonable accuracy. ─ INDIFFERENTNB, an improved version of the naive Bayes classifier based on the naive Bayes model, naive distributions, Bayesian model averaging and the principle of indifference that improves the quality of the probabilities of the maximum likelihood naive Bayes classifier. ─ STAN+BMA, a classification algorithm based on applying empirical local Bayesian model averaging to the stan (softened TAN) classifier and which improves its accuracy. ─ TBMATAN, a classification algorithm based on the computability of the averaging of TAN models under decomposable distributions over TANs and the principle of indifference that improves stan accuracy. ─ SSTBMATAN, an efficient approximation to TBMATAN which provides also improved accuracy. ─ MAPTAN, a classification algorihtm that computes the maximum a posteriori TAN model and improves STAN accuracy. ─ MAPTAN+BMA, a classification algorithm that computes the k maximum a posteriori TAN models and their relative weights efficiently and improves STAN accuracy and STAN+BMA accuracy and learning time. These results show that the joint application of Bayesian model averaging and a careful selection of the prior probability distribution over the set of models, following objective Bayesian techniques whenever it is possible, can provide significant improvements to classification algorithms.

Table of Contents Table of Contents (0.09 Mb)

Preview Preview (0.1 Mb)

Bibliographic information

Physical Description : XVII, 170 p. : gráf. ; 24 cm

ISBN: 978-84-00-08317-5

Publication: Bellaterra (España) : Consejo Superior de Investigaciones Científicas, 2005

Reference CSIC: 11139

Other data: Thesis

Buy the digital edition at

This eBook is available for free download

Free Downloads

Download eBook Download eBook (3.98 Mb)

This book was added to our online catalog on Thursday 01 October, 2015.