This course provides a systematic view of a range of contemporary machine learning algorithms, as well as an introduction to the theoretical aspects of the subject. Topics covered include the statistical learning framework, estimation theory, model complexity, mixture models, multilayer neural networks and deep learning, nonparametric methods, ensemble methods, and a brief outlook of other relevant topics in ML.
Appropriate for graduate students who have taken
CMSC 35300 / STAT 27700 (Mathematical Foundations of Machine Learning) (for CS/statistics major)
Or STAT 31430 (Applied Linear Algebra), or STAT 30900 (Mathematical Computation I — Matrix Computation), or STAT 24300 (Numerical Linear Algebra), or STAT 24500 (Statistical Theory and Methods II) (for statistics major),
Or equivalent (e.g. Part 1 covered by Mathematics for Machine Learning).
Instructor: Yuxin Chen <chenyuxin@uchicago.edu>
Course staff: Rong Jiang <hughjiang@uchicago.edu>, Yilin Chen <yilinchen@uchicago.edu>, Yuhan Philip Liu <yuhanphilipliu@uchicago.edu>
Format: Tu/Th, 9:30-10:50am CT @ RY 276.
Office hours
Tue: 3-4pm (Rong)
W: 11am-noon (Yilin)
Th: 11am-noon @ JCL 317 (Yuxin)
F: 3:00 pm - 4:00 pm (Yuhan Philip)
Discussion and Q&A: Via Ed Discussion (link provided on Canvas). The system is highly catered to getting you help quickly and efficiently from classmates, the TAs, and the instructors. Rather than emailing questions to the teaching staff, we encourage you to post your questions on Ed Discussion. For new users, see the following quick start guide: https://edstem.org/quickstart/ed-discussion.pdf
Assignment & Grading: Via Gradescope (link provided on Canvas)
Email policy: We will prioritize answering questions posted to Ed Discussion, not individual emails.
Pattern Recognition and Machine Learning; by Christopher Bishop. The textbooks will be supplemented with additional notes and readings.
Optional supplementary materials:
Probabilistic Machine Learning: An Introduction; by Kevin Patrick Murphy, MIT Press, 2021.
Understanding Machine Learning; by Shai Shalev-Shwartz and Shai Ben-David
Pattern Classification; by Duda, Hart, and Stork
Mathematics for Machine Learning; by Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong. Cambridge University Press, 2020.
Fall 2022, by Prof. Cong Ma
Spring 2020, co-taught by Prof. Rebecca Willett and Prof. Yuxin Chen.