Keras 2.x Projects

Naive Bayes algorithm

A Bayesian classifier is a classifier based on the application of Bayes' theorem. This classifier requires the knowledge of apriori and conditional probabilities related to the problem, quantities that, in general, are not known but are typically estimable. If reliable estimates of the probabilities involved in the theorem can be obtained, the Bayesian classifier is generally reliable and potentially compact.

In texts classification, with the term Bayesian classifier, we conventionally refer to the Naive Bayes classifier, that is, a simplified Bayesian classifier with an underlying probability model that makes the assumption of independence of the features, or assumes that the presence or absence of a particular feature ...