Machine Learning
COMP 5212, Spring 2026
The Hong Kong University of Science and Technology
Junxian He
Course description: this is an advanced machine learning course to provide a broad introduction to machine learning, covering foundational machine learning concepts, theory, algorithms, and applications. The topics include supervised learning (logistic regression, linear models, classification, SVM, kernal methods, naive Bayes), unsupervised learning (clustering, expectation maximization, graphical models, HMM), and reinforcement learning. It will include some optimization/learning topics (gradient descent, SGD, MLE and MAP estimation) as well. Certain aspects of deep learning are introduced（neural network basics, architectures, VAEs, GANs). The last lectures will give a general introduction to techniques in large language models.
Course Information
Course Logistics (Grading, Policy, etc.)
Time and Location
Lectures: Tue, Thu 4:30 PM - 5:50 PM at Room 4619 (Lift 31-32)
Course Staff and Office Hours
Instructor: Junxian He
TA1: Kashun Shum (ksshumab@connect.ust.hk)
TA2: Junlong Li (jlini@cse.ust.hk)
TA3: Hongxiang Li (hlihg@connect.ust.hk)
Contact and Communication
Canvas is the main platform for communication about technical questions of lecture contents and homeworks.
Prerequisites and Materials
Students are required to be familiar with probability and linear algebra, and able to program well in Python. The CMU 10701 self-assessment exam is a good resource to roughly give you a notion of the background that is required for this course.
This course does not have a textbook, but here are some helpful materials:
Stanford CS229 Notes
Probability Review
The Matrix Cookbook
Linear Algebra Review
Lecture Schedule
The lecture schedule below is tentative and subject to change. Slides will be posted here when available.
| Slides | Date | Topic | Readings | Assignments |
|---|---|---|---|---|
| Lecture 0 | 03/02 Tue | Introduction | ||
| Lecture 1 | 05/02 Thu | Math basics | ||
| Lecture 2 | 10/02 Tue | Linear Regression | ||
| Lecture 3 | 12/02 Thu | Logistic regression, Exponential Family | ||
| 17/02 Tue | Lunar New Year’s Day (Public Holiday) — No class | |||
| 19/02 Thu | The third day of Lunar New Year (Public Holiday) — No class | |||
| Lecture 4 | 24/02 Tue | Generalized linear models, Kernel Methods | Section 3 of Notes | |
| Lecture 5 | 26/02 Thu | SVM | Section 5, 6 of Notes | |
| Lecture 6 | 03/03 Tue | Generative Models | Section 4 of Notes | |
| Lecture 7 | 05/03 Thu | Naive Bayes, MLE, MAP | Section 4.2 of Notes, Sec 2.1-2.3.6 of Mitchell Ch2, Section 4.2, 4.6 of probml | |
| Lecture 8 | 10/03 Tue | Generalization, bias-variance tradeoff | Section 8.1-8.2 of Notes | |
| Lecture 9 | 12/03 Thu | Clustering, EM | Section 10, 11.1, 11.2 of Notes | |
| Lecture 10 | 17/03 Tue | Expectation Maximization | Section 11 of Notes | |
| Lecture 11 | 19/03 Thu | PCA | Section 12 of Notes | |
| Lecture 12 | 24/03 Tue | Probabilistic Graphical Models | Kevin Murphy’s Tutorial | |
| Lecture 13 | 26/03 Thu | HMM | Chapter 8, Speech and Language Processing | |
| Lecture 14 | 31/03 Tue | Mid-term exam | ||
| Lecture 15 | 02/04 Thu | HMM | Chapter 8, Speech and Language Processing | |
| 07/04 Tue | Mid-term Break (03/04–08/04) | |||
| Lecture 16 | 09/04 Thu | Neural Networks, backpropagation | Section 7.4 of Notes | |
| Lecture 17 | 14/04 Tue | Neural architectures | ||
| Lecture 18 | 16/04 Thu | Transformer, Variational autoencoder | The Illustrated Transformer, The Annotated Transformer | |
| Lecture 19 | 21/04 Tue | Variational autoencoder | Auto-Encoding Variational Bayes | |
| Lecture 20 | 23/04 Thu | GANs, Reinforcement Learning | Generative Adversarial Networks, OpenAI Spinning Up in RL | |
| Lecture 21 | 28/04 Tue | Large language models | ||
| Lecture 22 | 30/04 Thu | LLM Agents | ||
| Lecture 23 | 05/05 Tue | LLM Agents | ||
| Lecture 24 | 07/05 Thu | Wrap-up / Review |