Learning Semi Naïve Bayes Structures by Estimation of Distribution Algorithms

Recent work in supervised learning has shown that a surprisingly simple Bayesian classifier called naı̈ve Bayes is competitive with state of the art classifiers. This simple approach stands from assumptions of conditional independence among features given the class. Improvements in accuracy of naı̈ve Bayes has been demonstrated by a number of approaches, collectively named semi naı̈ve Bayes classifiers. Semi naı̈ve Bayes classifiers are usually based on the search of specific values or structures. The learning process of these classifiers is usually based on greedy search algorithms. In this paper we propose to learn these semi naı̈ve Bayes structures through estimation of distribution algorithms, which are non-deterministic, stochastic heuristic search strategies. Experimental tests have been done with 21 data sets from the UCI repository.