Unsupervised Learning

Description. Unsupervised Learning is a masters level course on foundations, methods, practice, and applications in machine learning from data without associated labels or outcomes. This course will focus on dimension reduction and clustering techniques while also covering graphical models, missing data imputation, anomaly detection, generative models, and others. The course will also emphasize conceptual understanding and practical applications of unsupervised learning in data visualization, exploratory data analysis, data pre-processing, and data-driven discovery. Prerequisites. STAT GR 5206 Statistical Computing and Intro to Data Science STAT GR 5241 Statistical Machine Learning (strongly recommended) STAT GR 5205 Linear Regression (recommended) STAT GR 5203 Probability (recommended) Students should also be familiar with linear algebra.