This course is about statistical learning methods and their use for data analysis. Upon completion, students will be able to build baseline models for real world data analysis problems, implement models using programming languages and draw conclusions from models. The course will cover principled statistical methodology for basic machine learning tasks such as regression, classification, dimension reduction and clustering. Methods discussed will include linear regression, subset selection, ridge regression, LASSO, logistic regression, kernel smoothing methods, tree based methods, bagging and boosting, neural networks, Bayesian methods, as well as inference techniques based on resampling, cross validation and sample splitting.

Repeat Rules

Course is not repeatable for credit.