**Fall 2022
Lectures: MWF 10:00am-10:50am
Modality: Hybrid.
Classroom for face-to-face lectures: NH 112.
**

- This is a hybrid class. Most lectures will be held ONLINE and not face-to-face. Students can attend every lecture live using Microsoft Teams.
- There will be six face-to-face lectures, at NH 112, on the following Fridays: September 23, September 30, October 7, October 21, October 28, November 4.

This course offers an introduction to machine learning. Topics include naive Bayes classifiers, linear regression, linear classificiers, neural networks and backpropagation, kernel methods, decision trees, clustering, and reinforcement learning. A strong programming background is assumed, as well as familiarity with linear algebra (vector and matrix operations), and knowledge of basic probability theory and statistics. Prerequisites: Admitted into an Engineering Professional Program, and C or better in each of the following: Algorithms (CSE 2320 or CSE 3318), Probability (IE 3301), and Linear Algebra (CSE 3380 or MATH 3330).

- Course Information and Policies: You can treat
this information as an unofficial version of the syllabus. The official version
is posted on Canvas.
- Schedule and Lecture Slides
- Assignments