Lectures for INFO8010 - Deep Learning, ULiège, Spring 2021.

• Instructor: Gilles Louppe
• Teaching assistants: Matthia Sabatelli, Antoine Wehenkel
• When: Spring 2021, Friday 9:00 AM
• Classroom: Lectures are virtual and broadcast on Youtube.
• Discussion: Join us on Discord (see invitation link in emails)

The goal of these two assignments is to get you familiar with the PyTorch library. Each homework should be done in groups of 2 or 3 (the same as for the project) and must be submitted on the Montefiore submission platform before 23:59 on the due date.

• Homework 1: Tensor operations, autograd and nn. Due by March 1.
• Homework 2: Dataset, Dataloader, running on GPU, training a convolutional neural network. Due by March 22.

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

See instructions in project.md.

Your task is to read and summarize a major scientific paper in the field of deep learning. You are free to select one among the following three papers:

• T. Karras al, "Analyzing and improving the image quality of StyleGAN", 2020. [pdf]
• E. Nalisnick, "Do Deep Generative Models Know What They Don't Know?", 2019 [pdf]
• M. Cranmer et al, "Discovering Symbolic Models from Deep Learning with Inductive Biases", 2020. [pdf]

You should produce a report that summarizes the problem that is tackled by the paper and explains why it is challenging or important, from the perspective of the wider research context. The report should outline the main contributions and results with respect to the problem that is addressed. It should also include a critical discussion of the advantages and shortcomings of the contributions of the paper. Further guidelines for writing a good summary can be found here (Section 2, "The summary").

Constraints:

• You can work in groups of maximum 3 students.
• You report must be written in English.
• 2 pages (excluding references, if any).
• Formatted using the LaTeX template template-report.tex.

Your report should be submitted by April 30, 2021 at 23:59 on the submission platform. This is a hard deadline.

• 2019-2020
• 2018-2019