- Lecture time: Tuesdays and Thursdays 1:45-3:15 PM
- Lecture location: Towne 100
- Instructors: Surbhi Goel (surbhig) and Eric Wong (exwong)
- Instructor office hours: Tuesdays at 3:30-4:30PM (Levine 505)
- Head TAs: Keshav Ramji (keshavr), and Wendi Zhang (wendiz)
- TAs: Abhinav Atrishi, Jordan Hochman, Bowen Jiang, Pavlos Kallinikidis, William Liang, Heyi Liu, David Zhi LuoZhang, Aryan Nagariya, Jeffrey Pan, Aditya Pratap Singh, and Tianyi Wei
- TA Office Hours: See Schedule Below
- Questions: We will be using Ed Discussion for all course communications. We encourage you to ask and answer any questions about the class (including homeworks, course schedule, exams, etc.) on Ed. You can post privately on Ed to contact the course staff (including instructors), if needed.
Waitlist information: To get off the waitlist, complete Homework 0 and send your solutions to the Head TAs. Permission for remaining seats will be granted to those that complete Homework 0. If you find Homework 0 to be very time consuming and extremely difficult, this course may not be right for you.
This course intends to provide a thorough modern introduction to the field of machine learning. It is designed for students who want to understand not only what machine learning algorithms do and how they can be used, but also the fundamental principles behind how and why they work. In particular, the course will focus on understanding the theoretical foundations of machine learning methods, along with applying them to real world data.
The course schedule contains the tentative schedule including topics we will cover in the lectures and any relevant reading material. Please refer here for the more information on the course along with the course policies.
Lectures will be held live every Tuesday and Thursday during 1:45-3:15 pm. Office hours will be held throughout the week. The time and location for the office hours will be posted soon.
Note that we will not be recording the lectures, so we highly encourage attending them live. Lecture notes and slides will be made available after the lecture. If you miss class, we encourage you to attend office hours.
Undergraduate level training or coursework on linear algebra, (multivariate) calculus, and basic probability and statistics,
Basic programming in Python,
Undergraduate level training or coursework in the analysis of algorithms.
We will not be explicitly following any single textbook in this course. The following books are useful for supplementary reading.
Machine Learning (ML) by Tom Mitchell. Available as PDF here. A classic introduction to machine learning that assumes no knowledge of statistics or artificial intelligence.
Elements of Statistical Learning (ESL) by Trevor Hastie, Robert Tibshirani and Jerome Friedman. Available as PDF here.
Probabilistic Machine Learning: An Introduction (PML) by Kevin Murphy. Available as PDF here.
Understanding Machine Learning: From Theory to Algorithms (UML) by Shai Shalev-Shwartz and Shai Ben-David. Available as PDF here. Refer to this book for a more detailed theoretical exposition of the material covered in class.
The following are helpful resources to review the mathematics that we will use in this course:
Mathematics for Machine Learning (MML) by Marc Deisenroth, A. Aldo Faisal, and Cheng Soon Ong. Available as PDF here.
Linear Algebra Review and Reference by Zico Kolter. Available as PDF here.