GRADUATE SEMINAR IN LEARNING THEORY

Credit Hours: 1,3 · Graduate

This course offers an in-depth exploration of the mathematical and computational foundations that underpin the algorithms and models used in machine learning. It is designed to delve into the theoretical aspects of machine learning, covering topics such as statistical learning theory, complexity theory, algorithmic efficiency, and differential privacy. The seminar aims to equip students with a robust understanding of how and why machine learning algorithms work, enabling them to design and implement more effective and efficient models. Students have the option of registering for a 3-credit hour project, which provides the opportunity to engage with the topic through a project for those seeking a more hands-on experience in the course. Recommended Prerequisite(s): machine learning or an algorithm course is strongly recommended.