Introduction to Statistical Learning

Overview

New techniques have emerged for both predictive and descriptive learning that help us make sense of vast and complex data sets. The particular focus of this course will be on regression and classification methods as tools for facilitating machine learning. In-class problem solving and discussion sessions will be used and computing will be done in R.

Instructors

• Lester Mackey Assistant Professor, Statistics

Topics Include

• Introduction to supervised learning
• Resampling, cross-validation and the bootstrap
• Model selection and regularization methods
• Tree-based methods, random forests and boosting
• Support-vector machines
• Nonlinear methods and generalized additive models
• Principal components and clustering

Prerequisites

First courses in statistics and/or probability, linear algebra, and computer programming.