Why Naive Bayes works

Naive Bayes is one of the strangest and at the same time one of the most practical models in machine learning. It is simple, almost primitive, makes a knowingly false assumption about the world – and still often works surprisingly well. It is especially useful for text classification, spam filtering, user intent detection, and simple diagnostics.

• MNIST: probabilistic digit classification (Naive Bayes)
• Case 1. Categorical features and frequencies
• Case 2. Spam filter on words (Bernoulli Naive Bayes)
• Case 3. Numeric features (Gaussian Naive Bayes)