Optimization and Machine Learning

Catalog description

This course provides an introduction to optimization and machine learning, i.e. how machines learn. It takes an in-depth look at objective, or loss, functions and how they are used to reduce error through feedback. It also takes a look at how that feedback enables machines to learn. Students gain an appreciation of the similarities in optimization and machine learning, as well as the differences. It also takes a look at all the challenges in training machine models including the local minima or maxima that affect machine learning. In addition, it discusses different methods that are applied to optimization and machine learning, e.g. gradient methods. (Prerequisites: MATH240, MATH328, DATS301)