Welcome to CIS5200: Machine Learning
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, and importantly, the Resources page for links
To register for the course all students need to apply via path. 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 live MW 1:45-3:15 Reviews are live F 1:45-3:15 Recitations are mandatory attendence Lecture recordings are on Canvas, 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. All regrade requests must be made within one week of your receiving the graded HW or exam.
For questions on course material and assignments, use Ed.