CS391L (Spring 25)

Machine Learning WB

Lectures: M/W 3:30-5:00PM (CT) (course calendar)
UT Unique No.: 51360

Instructor: Prof. Inderjit Dhillon
Teaching Assistant: Nilesh Gupta

Course Overview

This graduate course can be more aptly titled Fundamentals of Machine Learning. It is a gateway course to more advanced and specialized graduates courses on the topic, for example, courses that specialize in deep learning. To enjoy the course you should have a solid background in linear algebra, probability and statistics, and multivariate calculus. Refreshers on these topics will be done in class but they will necessarily be brief. If you are weak in any of these, you may find the course challenging. Topics covered include supervised methods (regression, classification), unsupervised methods (clustering, principal components analysis, non-linear dimensionality reduction), and self-supervised learning. The technical tools used in the course will draw from linear algebra, probability, multivariate statistics and optimization. Check reference books here.

Pre-requisites: Basics (undergraduate level) of linear algebra (M341 or equivalent).

Course sites

• Course Webpage: for all the important information in one place
• Ed Discussion: read/post *publicly* for technical questions and announcements, post *privately* for personal or administrative questions
• Canvas: for submission, grades on submitted work, etc

Grading

• 40% (4x10) Homeworks
• 30% Final Project
• 25% Midterm (In-person)
• 5% Class Participation

Rough List of Topics Covered

See full course schedule here.

• Least Squares Regression
• Review of Linear Algebra and Probability
• Matrix Completion
• Classification (Perceptron, SVM)
• Optimization (Gradient Descent, SGD, Coordinate Descent)
• Neural Networks
• Clustering
• Graph Analysis
• Kernel Methods
• Deep Learning Architectures (MLP, RNN, LSTM, Transformers)
• Other Topics in Deep Learning