General Information

A class that serves as an introduction to machine learning and focuses on supervised learning and the theary behind it.

Prerequisites

Discrete Structures (CS 2800) A probability theory class (for example BTRY 3080, ECON 3130, MATH 4710, or ENGRD 2700) A linear algebra class (for example MATH 2940)

Topics Covered

  • Regularized linear models
  • Boosting
  • Kernels
  • Deep networks
  • Generative models
  • Online learning
  • Ethical questions arising in ML applications

Workload

About 4 hours of work a week. Gets easier the more you know how to apply linear algebra in multivariate calculus. [Spring 2023]

General Advice

Have a real reason to take it. [Spring 2023]

Testimonials

Not very applicable to modern machine learning. Most useful thing is knowing how cost functions work. Probably better online classes for immediate application to physics. [Spring 2023]

Past Offerings

Semester Professor Median Grade Course Page
Spring 2023 Kilian Weinberger A- CS 4/5780 Spring 2023