Lectures for INFO8006 Introduction to Artificial Intelligence, ULiège, Fall 2026.
- Instructor: Gilles Louppe
- Teaching assistants: Fanny Bodart, Thomas Savary
- When: Fall 2026, Thursday 8:30 AM to 12:30 PM
- Classroom: B28/Mania Pavella
- Contact: info8006@montefiore.ulg.ac.be
- Discord: https://discord.gg/Y8UP2SBu2h
| Date | Topic |
|---|---|
| September 17 | Course syllabus [PDF] Lecture 0: Introduction to artificial intelligence [PDF] Lecture 1: Intelligent agents [PDF] |
| September 24 | Lecture 2: Solving problems by searching [PDF] Tutorial: Project 0, Project 0 bis |
| October 1 | Lecture 3: Games and adversarial search [PDF] Exercises 1: Solving problems by searching [PDF] [Solutions] |
| October 8 | Lecture 4: Quantifying uncertainty [PDF] Lecture 5: Probabilistic reasoning [PDF] Exercises 2: Games and adversarial search [PDF] [Solutions] |
| October 15 | Lecture 5: Probabilistic reasoning (continued) [PDF] Lecture 6: Reasoning over time [PDF] Exercises 3: Quantifying uncertainty [PDF] [Solutions] |
| October 16 | Deadline for Project 0 and Project 0 bis |
| October 22 | Lecture 6: Reasoning over time [PDF] (continued) Exercises 4: Probabilistic reasoning [PDF] [Solutions] |
| October 29 | No class |
| November 5 | Lecture 6: Reasoning over time [PDF] (continued) Lecture 7: Machine learning and neural networks [PDF] Exercises 5: Reasoning over time [PDF] [Solutions] |
| November 12 | Lecture 7: Machine learning and neural networks (continued) [PDF] Exercises 5: Reasoning over time (continued) [notebook] [Solutions] |
| November 19 | Lecture 7: Machine learning and neural networks (continued) [PDF] Exercises 6: Machine learning [PDF] [Solutions] |
| November 26 | Lecture 8: Making decisions [PDF] Exercises 6: Machine learning [PDF] (continued) [Solutions] |
| December 3 | Lecture 9: Reinforcement Learning [PDF] Exercises 7: Making decisions & RL [PDF] [Solutions] |
| December 10 | No lecture Exercises 7: Making decisions & RL [PDF] (continued) [Solutions] Exercises 8: Past exam |
| December 17 | No lecture |
- General instructions
- Part 0: (tutorial session in class, due by October 16)
- Part 1: Bayes Filter (TBD.)
- Part 2: Imitation Learning (TBD.)
The notebooks in demo/ run in a Python environment managed by uv. Install uv:
# macOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Then clone the repository and create the environment:
git clone https://github.com/glouppe/info8006-introduction-to-ai.git
cd info8006-introduction-to-ai
uv syncuv sync downloads Python 3.13 and installs the exact package versions pinned in uv.lock into a local .venv/ directory. PyTorch is kept apart, since it has no wheels for Intel Macs; the notebooks of lecture 7 need it, with
uv sync --extra torchLaunch Jupyter with
uv run jupyter labor, in VS Code, select .venv as the notebook kernel. To get new materials during the semester, run git pull followed by uv sync.
The slides are Markdown files rendered in the browser. To view them locally, serve the repository with Python's built-in web server from its root directory:
uv run python -m http.serverThen open http://localhost:8000/?p=lecture0.md, replacing lecture0.md with the lecture you want. Opening index.html directly from disk does not work, since browsers block it from loading the Markdown file.
- January 2019 (solutions)
- August 2019
- January 2020
- August 2020 (solutions)
- January 2021 (solutions)
- August 2021
- January 2022 (solutions)
- August 2022
- January 2023 (solutions)
- August 2023
- January 2024
- August 2024
- January 2025
- August 2025
- January 2026
- August 2026
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 |
|---|
| Lecture: Constraint satisfaction problems [PDF] |
| Lecture: Inference in Bayesian networks [PDF] |
| Lecture: Communication [PDF] |
| Lecture: Artificial general intelligence and beyond [PDF] |