Algorithms for Learning Augmented Bayesian Classifiers
نویسندگان
چکیده
The naïve Bayes classifier is built on the assumption of conditional independence between the attributes given the class. The algorithm has been shown to be surprisingly robust to obvious violations of this condition, but it is natural to ask if it is possible to further improve the accuracy by relaxing this assumption. We examine an approach where naïve Bayes is augmented by the addition of correlation arcs between attributes. We explore two methods for finding the set of augmenting arcs, a greedy hill-climbing search, and a novel, more computationally efficient algorithm that we call SuperParent. We compare these methods to TAN; a state-of the-art distribution-based approach to finding the augmenting arcs.
منابع مشابه
Comparing Bayesian Network Classifiers
In this paper, we empirically evaluate algorithms for learning four Bayesian network (BN) classifiers: Naïve-Bayes, tree augmented Naïve-Bayes (TANs), BN augmented NaïveBayes (BANs) and general BNs (GBNs), where the GBNs and BANs are learned using two variants of a conditional independence based BN-learning algorithm. Experimental results show the GBNs and BANs learned using the proposing learn...
متن کاملA Theoretical and Experimental Evaluation of Augmented Bayesian Classifiers
Naive Bayes is a simple Bayesian network classifier with strong independence assumptions among features. This classifier despite its strong independence assumptions, often performs well in practice. It is believed that relaxing the independence assumptions of naive Bayes may improve the performance of the resulting structure. Augmented Bayesian Classifiers relax the independence assumptions of ...
متن کاملTitle: Incremental Learning of Tree Augmented Naive Bayes Classifiers Authors:
Machine learning has focused a lot of attention at Bayesian classifiers in recent years. It has seen that even Naive Bayes classifier performs well in many cases, it may be improved by introducing some dependency relationships among variables (Augmented Naive Bayes). Naive Bayes is incremental in nature but, up to now, there are no incremental algorithms for learning Augmented classifiers. When...
متن کاملIncremental Learning of Tree Augmented Naive Bayes Classifiers
Machine learning has focused a lot of attention at Bayesian classifiers in recent years. It has seen that even Naive Bayes classifier performs well in many cases, it may be improved by introducing some dependency relationships among variables (Augmented Naive Bayes). Naive Bayes is incremental in nature but, up to now, there are no incremental algorithms for learning Augmented classifiers. When...
متن کاملBayesian network classifiers which perform well with continuous attributes: Flexible classifiers
When modelling a probability distribution with a Bayesian network, we are faced with the problem of how to handle continuous variables. Most previous works have solved the problem by discretizing them with the consequent loss of information. Another common alternative assumes that the data are generated by a Gaussian distribution (parametric approach), such as conditional Gaussian networks, wit...
متن کاملIncremental Augmented Naive Bayes Classifiers
We propose two general heuristics to transform a batch Hill-climbing search into an incremental one. Our heuristics, when new data are available, study the search path to determine whether it is worth revising the current structure and if it is, they state which part of the structure must be revised. Then, we apply our heuristics to two Bayesian network structure learning algorithms in order to...
متن کامل