Machine Learning
COMP 5212, Spring 2024
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: Wed, Fri 3:00 PM - 4:20 PM at Lecture Theater E
Course Staff and Office Hours
Instructor: Junxian He. Office Hour: Wed 4:30 PM - 5:30 PM at Room 3512
TA1: Kashun Shum. Office Hour: Wed 2:00 PM - 3:00 PM outside Room 3657
TA2: Chi Xu. Office Hour: Fri 6:00 PM - 7:00 PM at Room 4033
Contact and Communication
Canvas is the main platform for communication about technical questions of lecture contents and homeworks. Please do not directly email the teaching staff on technical questions which may easily get lost. The teaching staff will try to answer questions on Canvas in a prompt manner. Some rules:
- All announcements and communications will happen over Canvas
- Please utilize the Canvas Discussion page to ask questions. There are pre-existed discussion topics initiated by the staff such as lecture questions and each homework. Please post your questions in the respective thread, you are also encouraged to answer others’ questions if you know the answer.
- While we allow students to optionally post anonymous questions and answers on Canvas, please do not post anything inappropriate as anonymous users – in such cases, we will turn off the anonymous option.
- If you have non-technical, private matters, please email the teaching staff directly.
- Please consult the Course Logistics page before asking logistical questions.
- For longer discussions, please come to office hours.
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 | Date | Topic | Readings | Assignments |
|---|---|---|---|---|
| Lecture 0 | 31/01 Wed | Introduction | ||
| Lecture 1 | 02/02 Fri | Math basics | ||
| Lecture 2, draft2 | 07/02 Wed | Linear Regression | ||
| Lecture 3, draft3 | 09/02 Fri | Logistic regression, Exponential Family | ||
| Lecture 4, draft4 | 14/02 Wed | Generalized linear models, Kernel Methods | Section 3 of Notes | |
| Lecture 5, draft5 | 16/02 Fri | Kernel methods, SVM | Section 5 of Notes | |
| Lecture 6, draft6 | 21/02 Wed | SVM | Section 6 of Notes | |
| Lecture 7, draft7 | 23/02 Fri | SVM | Section 6 of Notes | HW1 Out |
| Lecture 8, draft8 | 28/02 Wed | Generative Models | Section 4 of Notes | |
| Lecture 9, draft9 | 01/03 Fri | 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 10, draft10 | 06/03 Wed | Generalization, bias-variance tradeoff | Section 8.1-8.2 of Notes | |
| Lecture 11, draft11 | 08/03 Fri | Clustering, EM | Section 10, 11.1, 11.2 of Notes | HW1 Due |
| Lecture 12, draft12 | 13/03 Wed | Expectation Maximization | Section 11 of Notes | HW2 Out |
| Lecture 13, draft13 | 15/03 Fri | PCA | Section 12 of Notes | |
| Lecture 14 | 20/03 Wed | mid-term exam | ||
| Lecture 15, draft15 | 22/03 Fri | Probabilistic Graphical Models | Kevin Murphy’s Tutorial | |
| Lecture 16, draft16 | 27/03 Wed | HMM | Chapter 8, Speech and Language Processing | |
| 28/03 Thu | HW2 Due | |||
| 29/03 Fri | Good Friday holiday | |||
| 30/03 Sat | Programming HW Out | |||
| 03/04 Wed | mid-term break | |||
| 05/04 Fri | mid-term break | |||
| Lecture 17, draft17 | 10/04 Wed | HMM | Chapter 8, Speech and Language Processing | |
| Lecture 18, draft18 | 12/04 Fri | Neural Networks, backpropagation | Section 7.4 of Notes | |
| Lecture 19, draft19 | 17/04 Wed | Neural architectures | HW3 Out | |
| Lecture 20, draft20 | 19/04 Fri | Transformer, Variational autoencoder | The Illustrated Transformer The Annotated Transformer | |
| Lecture 21, draft21 | 24/04 Wed | Variational autoencoder | Auto-Encoding Variational Bayes | |
| Lecture 22 | 26/04 Fri | GANs, Reinforcement Learning | ||
| 30/04 Tue | HW3 Due | |||
| 01/05 Wed | Labor day | |||
| Lecture 23 | 03/05 Fri | Language models | Programming HW Due | |
| Lecture 24 | 08/05 Wed | Pretraining | ||
| Lecture 25 | 10/05 Fri | Large language models |