Linear Discriminant Analysis Classifier

Linear Discriminant Analysis Classifier generates a linear decision boundary via fitting class conditional densities to the data and applying Bayes rule. In this model, all classes are assumed to share the same covariance matrix and fitted by the Gaussian density.

Advantages:

• It has a closed-form solution
• It is easy to implement
• It has no hyperparameters to tune

Disadvantages:

• It requires normal distribution assumption on features