Statistical Learning

Catalog description

This course provides an introduction to the statistical methods commonly used in learning from data. The course combines methodology with theoretical foundations and their computational aspects. The course aims to assist you in designing good learning algorithms and analyzing their statistical properties and performance guarantees. Fundamental principles and techniques of probabilistic thinking, statistical modeling, and data analysis are introduced. Topics covered include basic probability and statistics including events, conditional probabilities, Bayes theorem, random variables, probability distributions, and hypothesis testing. Building on these concepts, the course provides an in depth of coverage of supervised learning from data with focus on regression and classification methods. A few key unsupervised learning methods such as clustering (K-means and Hierarchical clustering) are covered. R is used for computing throughout the course. Three credits; one-hour laboratory.