Instructor	Lingpeng Kong (lpk AT cs.hku.hk)
Season	Spring 2023
Location	Tuesdays 12:30pm - 1:30pm & Fridays 12:30pm - 2:30pm @ MB167
	Chang Ma, Xie Zhang, Zhiheng Lyu
Textbook	Probabilistic Machine Learning: An Introduction
Tutorial	TBD

Course description:

This course introduces algorithms, tools, practices, and applications of machine learning. Topics include core methods such as supervised learning (classification and regression), unsupervised learning (clustering, principal component analysis), Bayesian estimation, neural networks; common practices in data pre-processing, hyper-parameter tuning, and model evaluation; tools/libraries/APIs such as scikit-learn, Theano/Keras, and multi/many-core CPU/GPU programming.

Prerequisites:

MATH1853 or MATH2101; and COMP2119 or ELEC2543 or FITE2020

Assessment:

50% continuous assessment, 50% examination

Schedule

Lecture	Topic/papers	Recommended reading	Materials
Part I: Basics
1	Introduction [slides]	[PML Ch. 1]
2	Foundations [slides]	[PML Ch. 2.1.1 - 2.4.1 - 2.5.2]
3	Logistic and Linear Regression [slides]	[PML Ch. 10.1 - 10.3] [PML Ch. 11.1 - 11.4]	[hw1] [temp]
4	Linear Discriminant Analysis, Naive Bayes Classifiers [slides]	[PML Ch. 9.1 - 9.3]
5	Neural Networks [slides]	[PML Ch. 13.1 - 13.5] [PML Ch. 15.1 - 15.3]
6	Supervised Learning (Review) [slides]		[MLAPP Reading Recommendation] [Tutorial 1]
7	Nonparametric Models (KNN and KDE) [slides]	[PML Ch. 16]
8	Clustering / Unsupervised Representation Learning [slides]	[PML Ch. 21.1 - 21.4] [PML Ch. 15.7]
9	Transformers [slides]	[Baahdanau et al, 2015] [Vaswani et al, 2017] [The Annotated Transformer]
10	Reinforcement Learning and AlphaGo [slides]	[Sutton and Barto, 2014] [Silver et al, 2016]

Assignments

Evaluation:

We will review your work individually to ensure that you receive due credit for your work. Please note that both your project output and logic will be considered for marking.

Policy and honor code:

You are free to discuss ideas and implementation details with other students. However, copying others’ codes will not help your study but jeopardize it. We will check your work against other submissions and Internet sources. It is easy to know if you did your own work or not. To be clear, we encourage you to discuss with your classmates but you MUST do your work independently and CANNOT simply copy. If plagiarism is identified, one may face serious consequences according to the Faculty and University policy.

Resources

Machine Learning Course by Andrew Ng

Machine Learning Course by Tom Mitchell