← Open Source
glouppe

info8010-deep-learning

Lectures for INFO8010 Deep Learning, ULiège.

TutorialsML/AI fundamentalsJupyter Notebook
Open on GitHub
Momentum
+0stars in 24 hours0.0%
1.29k
Stars
331
Forks
+0
This week
9
Contributors
Created 2018-03-14 · Updated 2026-09-17 · #10807 today
Top developers
glouppepaintceptionAWehenkel
README

INFO8010 - Deep Learning

Lectures for INFO8010 Deep Learning, ULiège, Spring 2026.

  • Instructor: Gilles Louppe
  • Teaching assistants: Fanny Bodart, Elise Faulx, Julien Brandoit, Sacha Peters
  • When: Spring 2026, Friday 8:30 AM
  • Classroom: B28 / Mania Pavella amphitheater
  • Discord: https://discord.gg/5yZqTZhXFW

Agenda

Date Topic
February 6 Course syllabus [PDF]
Lecture 0: Introduction [PDF]
Lecture 1: Fundamentals of machine learning [PDF]
Code 1: Polynomial regression
February 13 Lecture 2: Multi-layer perceptron [PDF]
Code 2a: Space stretching
Code 2b: Spiral classification
February 20 Lecture 3: Automatic differentiation [PDF]
Code 3a: Automatic differentiation in Pytorch
Code 3b: Differentiable fluid simulation
February 27 Lecture 4: Training neural networks [PDF]
Code 4a: Training neural networks
Code 4b: Initialization
March 6 Lecture 5: Convolutional neural networks [PDF]
Code 5a: Convolutional neural networks
Code 5b: From ResNet to ConvNeXt
March 13 Lecture 6: Computer vision [PDF]
Code 6: UNet
March 15 Deadline for Homework 1
March 20 Lecture 7: Attention and transformers [PDF]
Code 7: Vision transformer
March 27 Lecture 8: GPT, from scratch! [PDF]
Code 8: GPT, from scratch!
March 29 Deadline for Homework 2
Deadline for project proposal
April 3 Lecture 9: Graph neural networks [PDF]
Code 9: Graph neural networks
April 10 Lecture 10: Uncertainty [PDF]
Code 10: Density estimation
April 17 Lecture 11: Auto-encoders and variational auto-encoders [PDF]
Code 11: Variational auto-encoders
May 8 Lecture 12: Diffusion models [PDF]
May 14 Project deadline
May 15 Poster session

Homeworks

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, autograd and nn. Due by March 15, 2026.
  • Homework 2: Dataset, Dataloader, running on GPU, training a convolutional neural network. Due by March 29, 2026.

Homeworks are optional. If submitted, each homework will account for 5% of the final grade.

Project

See instructions in project.md.

Archives

Previous editions

Archived lectures

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]
Nearby in the ranking
Similar items