This is an introductory course on deep learning. The topics include, but not limited to, machine learning, deep neural network, regularization, optimization, graph learning and generative models. The students who successfully finish this course will gain knowledge on representation learning via deep learning.

*Important notice for Fall 2025*
This course will be taught quite differently to previous years. The main difference is that we will not only have the classic "information delivery" sessions, but also rather intensive and frequent *discussion* sessions. This will be done by providing agenda for discussion before the class so people come prepared; students will be required to write their own thoughts and reflections on the discussion afterwards. Subsequently, there will be no exams or final projects, but only some quizzes from time to time. Undergrad students are welcome to take this course; as long as they have basic knowledge of mathematics and computing skills it should be fairly straightforward to follow through. (last updated on 22 July 2025)

Basic knowledge of mathematics (such as linear algebra, calculus, probability) and computing skills (how to write a program).

Quiz: 50%
Class participation: 50% (details to be announced later)

*The criteria above is subject to change.

https://udlbook.github.io/udlbook/

Chapter 1 - Introduction
Chapter 2 - Supervised learning
Chapter 3 - Shallow neural networks
Chapter 4 - Deep neural networks
Chapter 5 - Loss functions
Chapter 6 - Training models
Chapter 7 - Gradients and initialization
Chapter 8 - Measuring performance
Chapter 9 - Regularization
Chapter 10 - Convolutional networks
Chapter 11 - Residual networks
Chapter 12 - Transformers
Chapter 13 - Graph neural networks
Chapter 14 - Unsupervised learning
Chapter 15 - Generative adversarial networks
Chapter 16 - Normalizing flows
Chapter 17 - Variational autoencoders
Chapter 18 - Diffusion models
Chapter 19 - Deep reinforcement learning
Chapter 20 - Why does deep learning work?
Chapter 21 - Deep learning and ethics

*The course schedule is subject to change.

information delivery followed by discussions and presentations