CSE446 - Machine Learning

Sewoong Oh
University of Washington
MWF 9:30-10:20, CSE2 G20

Announcement

  • The midterm exam is scheduled on Nov 1st, in class

  • Course staff can be reached at cse446-staff@cs.washington.edu

  • Attendance is expected, and no video recording of the lecture will be provided.

  • Please submit evaluation of the course and sections at the end of the quarter. Provinding a proof of the evaliation (but NOT the evaluation itself) will give you extra 1% towards the final grade.

  • Past year Exams will not be posted.

  • Assignment solutions will not be posted.

  • Welcome to CSE446.

Calendar

Course Description

It is hard to imagine anything more fascinating than automated systems that improve their own performance. The study of learning from data is commercially and scientifically important. This course is designed to provide a thorough grounding in the methodologies, technologies, and algorithms of machine learning. The topics of the course draw from classical statistics, from machine learning, from data mining, and from statistical algorithmics.

Students entering the class should have a pre-existing working knowledge of probability, statistics and algorithms, though the class has been designed to allow students with a strong numerate background to catch up and fully participate.

Prerequisite

  • CSE332 (Data Structures and Parallelism); and

  • Either CSE312 (Foundations od Copmuting II), STAT/MATH390 (Statistical Methods in Engineering and Science), or STAT391 (Statistics of Data Science).

Instruction Times

  • Lecture: MWF 9:30-10:20, CSE2 G20

  • Office Hours: see people

  • Sewoong's Office hours: Mondays 11:00-12:00 in CSE2 207

  • TA Sessions

    • AA Thursdays 8:30-9:20, MGH 238, Instructor: Leo Liu

    • AB Thursdays 9:30-10:20, MUE 154, Instructor: Michael Zhang

    • AC Thursdays 10:30-11:20, CMU B006, Instructor: Romain Camilleri

    • AD Thursdays 11:30-12:20, MEB 238, Instructor: Sam Gao and Anirudh Canumalla

    • AE Thursdays 12:30-1:20, ECE 042, Instructor: Eric Chan and Ivan Montero

Grading

  • 5 Assignments (50%)

  • Midterm Exam (20%)

  • Final Exam (30%)

Textbooks