Kernel Methods

“Once you learn to read, you will be forever free..”
– Frederick Douglass

In this section, we encounter another very popular non-parametric model. Unlike the models we saw previously, this models likes to keep the training dataset \mathcal{D} around. Thus, the effective number of model parameters grows with the size of the training data.

TipChapter Objectives

In this chapter, we will learn the following:

  1. KNN classifier

  2. scikit-learn implementation

  3. Applications of KNN to various popular datasets

  4. Model section criterion: ROC & AUC