Lectures for INFO8010 Deep Learning, ULiège, Spring 2024.
- Instructor: Gilles Louppe
- Teaching assistants: Arnaud Delaunoy, François Rozet, Yann Claes, Victor Dachet
- When: Spring 2024, Friday 8:30 AM
- Classroom: R7 / B28
- Discord: https://discord.gg/5yZqTZhXFW
| Date | Topic |
|---|---|
| February 9 | Course syllabus [PDF] [video] Lecture 0: Introduction [PDF] [video] Lecture 1: Fundamentals of machine learning [PDF] [video] |
| February 16 | Lecture 2: Multi-layer perceptron [PDF] [video] [code 1, code 2] |
| February 23 | Lecture 3: Automatic differentiation [PDF] [video] [code] |
| March 1 | Lecture 4: Training neural networks [PDF] [video] |
| March 4 | Deadline for Homework 1 |
| March 8 | Lecture 5: Convolutional neural networks [PDF] [video] [code] |
| March 15 | Lecture 6: Computer vision [PDF] [video] Invited talk: François Lievens (aiHerd) |
| March 18 | Deadline for Homework 2 |
| March 18 | Deadline for the project proposal |
| March 22 | Lecture 7: Attention and transformers [PDF] [video] |
| March 29 | Code: GPT, from scratch! Lecture 8: LLMs and foundation models [PDF] |
| April 5 | Lecture 9: Graph neural networks [PDF] |
| April 12 | Lecture 10: Uncertainty [PDF] [video] |
| April 19 | Lecture 11: Auto-encoders and variational auto-encoders [PDF] [video] [code] |
| May 10 | Lecture 12: Diffusion models [PDF] |
| May 17 | Deadline for the project |
The goal of these two assignments is to get you familiar with the PyTorch library. You can find the installation instructions in the Homeworks folder. Each homework should be done in groups of 2 or 3 (the same as for the project) and must be submitted before 23:59 on the due date. Homeworks should be submitted on Gradescope.
- Homework 1: Tensor operations,
autogradandnn. Due by March 4, 2024. - Homework 2: Dataset, Dataloader, running on GPU, training a convolutional neural network. Due by March 18, 2024.
Homeworks are optional. If submitted, each homework will account for 5% of the final grade.
See instructions in project.md.
TBD.
Due to progress in the field, some of the lectures have become less relevant. However, they are still available for those who are interested.
| Topic |
|---|
| Recurrent neural networks [PDF] [video] |
| Generative adversarial networks [PDF] [video] |
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent