Spring 2024

Theory of Machine Learning

Listed in: Computer Science, as COSC-347


Scott P. Alfeld (Section 01)


This course covers the mathematical underpinnings of machine learning. It provides a rigorous treatment of questions such as: What does it mean to learn? How can a machine learn? What concepts are learnable? How can we quantify the resources needed to learn? Students should be familiar with common learning paradigms (classification and regression) and algorithms (e.g., linear regression, decision trees, k-nearest neighbors) and comfortable with mathematical proofs. After a brief review of how various machine learning algorithms work, this course will focus on why they work.

Requisite: COSC-241 or COSC-247 and MATH-220 or MATH-271 or MATH-272. Spring semester: Assistant Professor Alfeld.

How to handle overenrollment: Preference is given to Computer Science majors.

Students who enroll in this course will likely encounter and be expected to engage in the following intellectual skills, modes of learning, and assessment: Quantitative work.


2022-23: Not offered
Other years: Offered in Spring 2024