DSC5001: Statistical Machine Learning I
This course develops the statistical foundations of machine learning through probability, inference, regression, classification, and unsupervised learning. Topics include parameter estimation and bootstrap, linear and nonlinear regression, smoothing and Gaussian processes, classification, tree-based methods, support vector machines, principal component analysis, and clustering.
Course Materials
Syllabus · All downloads are PDFs. Tutorials include solutions.
| Week | Topic | Lecture | Tutorial with Solutions |
|---|---|---|---|
| 1 | Statistical Learning and Probability | ||
| 2 | Method of Moments and Maximum Likelihood | ||
| 3 | Bootstrap and Statistical Uncertainty | ||
| 4 | Linear Regression | ||
| 5 | Nonlinear Regression and Splines | ||
| 6 | Modern Machine Learning and Project Directions | Not posted |
Past papers and example code: to be posted.
Assignments
| Assignment | Questions | Solutions |
|---|---|---|
| Assignment 1 | PDF · 9 pages | PDF · 14 pages |
Course Information and Schedule
- Institution
- City University of Hong Kong (Dongguan)
- Term
- Fall 2026 · 3 credits · 13 teaching weeks
- Schedule
- Lecture: Monday, 2:00 PM–3:50 PM
Tutorial: Monday, 4:00 PM–4:50 PM - Venue
- AC5-515
- Instructor
- Kangning Cui · Email · AC4-422
Assessment
- Assignments 10%
- Midterm Examination 20%
- Group Project 20%
- Final Examination 50%
Assignments combine statistical reasoning and implementation. The group project develops and evaluates a statistical machine learning solution for a real-world problem.