Machine learning explores the study and construction of algorithms that can learn from historical data and make inferences about future outcomes. This study is a marriage of algorithms, computation, and statistics so this class will have healthy doses of each. The goal of this course is to provide a thorough grounding in the fundamental methodologies and algorithms of machine learning.
Prerequisites: Students entering the class should be comfortable with programming and should have a pre-existing working knowledge of linear algebra (MATH 308), vector calculus (MATH 126), probability and statistics (CSE 312/STAT390), and algorithms. For a brief refresher, we recommend that you consult the linear algebra and statistics/probability reference materials on the Textbooks page.
Grading: Your grade will be based exclusively on 5 homework assignments: HW0 (12%), HW1 (22%), HW2 (22%), HW3 (22%), HW4 (22%). There are no exams or credit given in any way other than the homeworks (e.g., no credit given for attending lecture or section).
In Winter 2022, we offer the undergraduate machine learning course CSE 446. In other quarters, we offer CSE446/546, which is a concurrent tracks for under graduate and graduate level machine learning courses. So if you are looking for a more challenging course, please consider taking it in the Spring 2022.
You are not required to attend sections, but we highly encourage you to. It is a great place to ge to konw your TAs and learn beyond what is taught in lectures. Due to restrictions on the number of people in each classroom due to COVID, you should attend the section that you are enrolled in. Given that morning sections have had extremely low attendance historically, we are planning to cancel morning sections and find better use of TAs' time on answering your questions on EdStem and offering more Office hours. More details will follow.