Skip to content

Welcome to CSCI 5525!

Extended waitlist of the course

If you are not on the waitlist in MyU and would like to take this course, please add yourself in this form. Please also attend all lectures and mark your attendances. We want to make sure that you have followed along.

Syllabus

Machine Learning is about how we make predictions and decisions based on data. This course covers the theory and practical algorithms for machine learning from a variety of perspectives. We cover topics such as support vector machines, neural networks, boosting, statistical learning methods, unsupervised learning, online learning, and reinforcement learning.

Logistics

  • Course: CSCI 5525, Fall 2019
  • Location: Mechanical Engineering 108
  • Time: Tuesdays and Thursdays, 11:15 AM‑12:30 PM

Communication

  • Canvas: We will be using Canvas for all assignments and grades. Please also post all questions on Canvas as discussions instead of sending emails.

  • Email: If you email your instructor, you must include the substring "CSCI 5525" to begin a meaningful subject line and have tried to resolve the issue appropriately otherwise. For example, you should post questions about course material and homework assignments on Canvas first, and then use emails only after an appropriate amount of time has passed without a response. Please use your UMN email account.

Course Staff

  • Instructor: Steven Wu

    • Email: zsw@umn.edu
    • Office hours: Tuesday 16:00-17:00 PM
    • Location: 6-225E Keller Hall
  • Teaching Assistants:

    • Arun Kumar
      • Email: kumar250@umn.edu
      • Office hours: Monday 2:00-3:00 PM
      • Location: 2-246 Keller Hall
    • Abinash Sinha
      • Email: sinha160@umn.edu
      • Office hours: Wednesday 5:00-6:00 PM
      • Location: 2-246 Keller Hall

FAQ

  • Who should take this course?

Advanced undergraduates or graduate students interested in machine learning.

  • What are the pre-requisites?

Ideally you will have completed CSCI 5521 or equivalently other introduction to machine learning courses. You should also have (1) undergraduate level training or coursework in linear algebra, multivariate calculus, and basic probability and statistics, and (2) programming skills with Python.

  • Will there be programming?

Yes, there will be programming.

  • Will there be math?

Yes, a lot.