News
- Jan 09: Welcome all the students! Wish you enjoy our Machine Learning course and have a splendid semester!
Information
- Lectures
- Tuesday, 8:30 - 10:15 am, Science Centre L1 Wednesday, 8:30 - 9:15 am, Science Centre L1
- Tutorials
- Wednesday, 9:30 - 10:15 am, Science Centre L1
- Additional Tutorials
- Tuesday, 6:30 - 7:15 pm, ERB 402 (~20 seats, for students with time conflict with Wednesday's tutorial)
- Instructor
- Prof. Liwei WANG
- Office Hour
- Wednesday 3 - 5 pm. Please send an email to course instructor to make an appointment at least two days in advance.
- Teaching Assistant
- Ziyuan Hu Shuo Liang Yue Qiu Duo Zheng Zixiao Wang
- Announcement
- All updates will be sent to your emails. Please check your university emails.
- Grading
- Assignments (40%) + Final Examination (60%)
- Book References
-
- Learning from Data, by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin
- Machine Learning: A Probabilistic Perspective, by Kevin P. Murphy
- Pattern Recognition and Machine Learning, by Christopher M. Bishop
- Abundant resources available on the web
Tutorial sessions would be the fastest and clearest way to discuss any problem. You are also welcomed to send emails to the instructor and the TAs.
Lectures
All related lecture materials will be posted on Blackboard → Course Contents.
Note: Lecture slides cannot be distributed outside the class.
The following schedule (tentative) are subject to minor modifications.
| Week | Date | Topic | Other |
|---|---|---|---|
| 1 | Jan 09, 10 | Introduction to Machine Learning | |
| 2 | Jan 16, 17 | Why Machine Learning is Feasible? | |
| 3 | Jan 23, Jan 24 | Training versus Testing - Theory of Generalization | |
| 4 | Jan 30, Jan 31 | Training versus Testing - VC Dimension | Release of Assignment 1 on Saturday evening |
| 5 | Feb 06, 07 | Training versus Testing - Bias Variance Tradeoff | |
| 6 | Feb 20, 21 | Models, Overfitting and Regularization | Submission of Assignment 1 before Sunday 11:59 pm Release of Assignment 2 on Saturday evening |
| 7 | Feb 27, Feb 28 | Bayesian Learning | |
| - | Mar 5, 6 | Reading Week | Submission of Assignment 2 before Sunday 11:59 pm |
| 8 | Mar 12, 13 | Gaussian Mixture Models, and EM Algorithm | Release of Assignment 3 on Saturday evening |
| 9 | Mar 19, 20 | Optimization | |
| 10 | Mar 26, 27 | Online Learning and Boosting | Release of Assignment 4 on Saturday evening Submission of Assignment 3 before Sunday 11:59 pm |
| 11 | Apr 2, 3 | Reinforcement Learning: Part 1 | |
| 12 | Apr 09, 10 | Reinforcement Learning: Part 2 | Release of Assignment 5 on Saturday evening Submission of Assignment 4 before Sunday 11:59 pm |
| 13 | Apr 16, 17 | Machine Learning Applications: How does ChatGPT work? | Submission of Assignment 5 before April 29 11:59 pm |
Assignments (40%)
There will be five assignments in total.
- Assignments may involve question sets and Python coding
- Points allocation to assignments is: 8 + 8 + 8 + 8 + 8 = 40%
- All five assignments must be done independently by yourself
- You are encouraged to either typeset your solution in LaTeX or Word
- You can also scan or take photos of your handwritten solution and bundle your scans/photos into one single PDF file
Unless further notice, all written answers for the question sets should be submitted in a single PDF file. If there is coding involved, please also compress the related codes into a ZIP file and submit it along with your PDF answer. The PDF file should be accepted by VeriGuide before submission. All the submissions should be made via Blackboard by 11:59 pm.
Final Examination (60%)
More information about the written Final Examination will be released later.
Course Policy
- Academic Honesty Policy
- Late Submission Policy
The Chinese University of Hong Kong places very high importance on honesty in academic work submitted by students, and adopts a policy of zero tolerance on academic dishonesty.
All submissions of assignments, project, etc. should be processed by VeriGuide first.
No late assignments will be accepted. NO EXCEPTION!!!