Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
Machine learning, neural and statistical classification
Machine learning, neural and statistical classification
Enhancements to the data mining process
Enhancements to the data mining process
On the Optimality of the Simple Bayesian Classifier under Zero-One Loss
Machine Learning - Special issue on learning with probabilistic representations
Machine Learning
Semi-Naive Bayesian Classifier
EWSL '91 Proceedings of the European Working Session on Machine Learning
Induction of Recursive Bayesian Classifiers
ECML '93 Proceedings of the European Conference on Machine Learning
Naive Bayesian Classifier Committees
ECML '98 Proceedings of the 10th European Conference on Machine Learning
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Adjusted Probability Naive Bayesian Induction
AI '98 Selected papers from the 11th Australian Joint Conference on Artificial Intelligence on Advanced Topics in Artificial Intelligence
Tractable Average-Case Analysis of Naive Bayesian Classifiers
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Combining Classifiers with Meta Decision Trees
Machine Learning
DS '01 Proceedings of the 4th International Conference on Discovery Science
Hybrid random subsample classifier ensemble for high dimensional data sets
International Journal of Hybrid Intelligent Systems
| Hi-index | 0.00 |
Naive Bayes is a well known and studied algorithm both in statistics and machine learning. Although its limitations with respect to expressive power, this procedure has a surprisingly good performance in a wide variety of domains, including many where there are clear dependencies between attributes. In this paper we address its main perceived limitation - its inability to deal with attribute dependencies. We present Linear Bayes that uses, for the continuous attributes, a multivariate normal distribution to compute the require probabilities. In this way, the interdependencies between the continuous attributes are considered. On the empirical evaluation, we compare Linear Bayes against a naive-Bayes that discretize continuous attributes, a naive-Bayes that assumes a univariate Gaussian for continuous attributes, and a standard Linear discriminant function. We show that Linear Bayes is a plausible algorithm, that competes quite well against other well established techniques.