CS/DSC/AI 391L
A graduate-level machine learning course at UT Austin
I am teaching assistant (technically a learning facilitator, but it’s the same thing) for a UT Austin graduate-level machine learning course for computer science, data science, and artificial intelligence master’s students.
The course is very much a theoretical introduction to ML. I would honestly call it an introduction to statistical learning theory rather than an introduction to ML.
The coursebook is Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David. If you’ve ever wanted to learn more about machine learning beyond clicking a run button on a scikit-learn project, I highly recommend reading the book. Recommended prerequisites are an understanding of probability theory, linear algebra, and calculus. Note that the course does not cover deep learning or reinforcement learning.
My duties are to hold office hours, answer questions on online message boards, grade homework and exams, and to keep an eye on academic integrity violations.
So far, through Summer and Fall 2024, there have been 600 students I have been responsible for in this course.
I may post some notes I’ve written here about course material in the future.
Topics:
- Mistake-Bounded Learning
- PAC Learning
- VC Dimension (Optional)
- Decision Trees
- Random Forests
- Gradient Descent
- Perceptron Learning
- Boosting
- Linear Regression
- Logistic Regression
- SVD/PCA
- Basic Statistics
- Maximum Likelihood Estimation
- Bayesian Inference
- Gaussian Mixture Models and EM
- Multivariate Normal
- Kernel Regression
- SVM (Optional)
- Neural Networks