36-665 Special Topics: Conceptual Foundations of Statistical Learning

9 units, Carnegie Mellon University

This class is an introduction to the foundations of statistical learning theory, and its uses in designing and analyzing machinelearning systems. Statistical learning theory studies how to fit predictive models to training data, usually by solving an optimization problem, in such a way that the model will predict well, on average, on new data. The course will focus on the key concepts and theoretical tools, at a level accessible to students who have taken 36401 and its prerequisites. The course will also illustrate those concepts and tools by applying them to carefully selected kinds of machine learning systems such as kernel machines. Students wanting exposure to a broad range of algorithms and applications would be better served by 36462662 Data Mining. This class is for those who want a deeper understanding of the principles underlying all machine learning methods.

Prerequisites: none listed

Courseweave needs JavaScript to show sections, workloads and planning tools.