Estimating Continuous Distributions in Bayesian Classifiers Export

@inproceedings{citeulike:373647, abstract = {When modeling a probability distribution with a Bayesian network, we are faced with the problem of how to handle continuous variables. Most previous work has either solved the problem by discretizing, or assumed that the data are generated by a single Gaussian. In this paper we abandon the normality assumption and instead use statistical methods for nonparametric density estimation. For a naive Bayesian classifier, we present experimental results on a variety of natural and artificial domains,...}, author = {John, George H. and Langley, Pat}, citeulike-article-id = {373647}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.3257}, keywords = {cs, frameshift, fs-bib}, pages = {338--345}, posted-at = {2008-02-28 21:02:18}, priority = {2}, title = {Estimating Continuous Distributions in Bayesian Classifiers}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.3257} }

TY - CONF ID - citeulike:373647 L3 - citeulike-article-id:373647 N2 - When modeling a probability distribution with a Bayesian network, we are faced with the problem of how to handle continuous variables. Most previous work has either solved the problem by discretizing, or assumed that the data are generated by a single Gaussian. In this paper we abandon the normality assumption and instead use statistical methods for nonparametric density estimation. For a naive Bayesian classifier, we present experimental results on a variety of natural and artificial domains,... EP - 345 TI - Estimating Continuous Distributions in Bayesian Classifiers SP - 338 KW - cs KW - frameshift KW - fs-bib AU - John, George AU - Langley, Pat UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.3257 ER -