Supervised learning

Objectives

Distinguish between supervised and unsupervised learning
Select and implement different supervised learning methods
Compare the performance of competing learning methods

Course outline

Supervised learning – definition and general concepts,
k nearest neighbors (KNN ),
Naive Bayesian Classifiers,
Discriminant analysis (factorial and Bayesian)
Tree-based segmentation (CART, CHAID), Probability Estimation Trees, multi-target trees (Ctree).
Comparison of methods (LIFT, ROC, advantages and disadvantages of the various methods presented).

Prerequisites

Multivariate Exploratory Statistics 1A, projection and optimization (Lagrangian)