This course provides a thorough modern introduction to the field of machine learning. It is designed for students who want to understand not only what machine learning algorithms do and how they can be used, but also the fundamental principles behind how and why they work. See the Course Description and Lectures for more details.
Prerequisites are a basic knowledge of linear algebra (matrices, eigenvectors), probability, statistics, programming in python,and latex. (See the Course Description)
To register for the course all non-CIS students will need to fill out the CIS waitlist form. We will try our best to accommodate as many qualified students as possible, but we typically receive more registration requests than course capacity. Registration/permit decisions will be based primarily on student backgrounds and on departmental waitlist policies.
Lectures are in Heilmeier Auditorium (Towne 100), MW 10:30–12:00, F 9:30am-11:00am . Lecture recordings are on Canvas, but note that lectures that use the board are very hard to follow from the recordings and that recordings sometimes fail. Attendance is strongly encouraged.
The Schedule, including exam dates, is in Lectures.
Assignments will be posted in Canvas. Your homeworks will be submitted via Gradescope. Coding will be in Python Jupyter notebooks using Numpy/SKLearn/Pytorch. Written homeworks will be in LATEX.
For questions on course material and assignments, use Piazza.