#multiple discriminant analysis

Dimensionality Reduction via Linear Discriminant Analysis

In my previous post, I had written about principal component analysis (PCA) for dimensionality reduction. In PCA, the class label of each and every example, even if available, is ignored and only the feature values from each example are considered. Thus, PCA is considered an unsupervisedapproach.  The emphasis in PCA is to preserve data variability as much as possible while reducing the…