CSE 251C - ML: Machine Learning Theory - Moshkovitz [SP21]
Course Website: https://sites.google.com/eng.ucsd.edu/cse-251c/home
Piazza: piazza.com/ucsd/spring2021/cse251c
Class: Tuesday and Thursday 9:30-10:50am
Zoom link, password: cse251C
Lecture recordings are available in the Zoom LTI PRO tab on canvas.
Course Schedule:
-
Intro to course and concentration inequalities
-
Statistical learning framework and probably approximately correct learning of finite classes
-
The Vapnik–Chervonenkis dimension
-
Agnostic learning and the uniform convergence property
-
Proof of the fundamental theorem of statistical learning
-
Explainable machine learning
-
Final presentations
Announcements:
Presentation schedule: here
Recordings for classes 5+6:
Grades:
-
Homeworks 30%
-
Final project 70%
-
Presentation 30%
-
Submitted work 30%
-
2 meetings with staff 10%
-
Supplementary readings:
-
S. Shalev-Shwartz, S. Ben-David, Understanding Machine Learning: From Theory to Algorithms. http://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/
-
C. Molnar, Interpretable Machine Learning: A Guide for Making Black Box Models Explainable.
https://christophm.github.io/interpretable-ml-book/
-
R. Schapire, Y. Freund, Boosting: Foundations and algorithms.
Course Summary:
| Date | Details | Due |
|---|---|---|