wzshtuhao / info8010-deep-learning

Lectures for INFO8010 - Deep Learning, ULiège

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

INFO8010 - Deep Learning

Lectures for INFO8010 - Deep Learning, ULiège, Spring 2020.

Agenda

Date Topic
February 7 Outline [PDF]
Lecture 0: Introduction [PDF]
Lecture 1: Fundamentals of machine learning [PDF]
Tutorial 1: Installation and tensor operations
February 14 Lecture 2: Neural networks [PDF]
Tutorial 2: Using pre-trained neural networks
February 21 Lecture 3: Convolutional networks [PDF]
Tutorial 3: Backpropagation
February 28 Lecture 4: Computer vision [PDF]
Q&A session
March 6 Lecture 5: Training neural networks [PDF]
Tutorial 4: Neural networks with PyTorch
Project proposal
March 13 Lecture 6: Recurrent neural networks [PDF] (Cancelled)
March 20 Lecture 6: Recurrent neural networks [PDF] [Podcast]
March 27 Lecture 7: Auto-encoders and generative models [PDF] [Podcast]
April 3 Lecture 8: Generative adversarial networks [PDF] [Podcast]
Tutorial 5: Convolutional neural networks
April 10 Lecture 9: Uncertainty [PDF] [Podcast]
Q&A session
April 24 Lecture 10: Deep reinforcement learning (guest lecture)
Tutorial 6: Deep reinforcement learning
Reading assignment
May 1 Q&A session (10:00 AM, Lifesize)
May 8 Q&A session (10:00 AM, Lifesize)
May 15 Q&A session (10:00 AM, Lifesize)
Project code and report

Project

See instructions in project.md.

Reading assignment

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:

  • J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger", 2017. [pdf]
  • A. Vaswani et al, "Attention is all you need", 2017. [pdf]
  • M. Geiger et al, "Scaling description of generalization with number of parameters in deep learning", 2019. [pdf]

You should produce a report that summarizes the problem that is tackled by the paper and explains why it is challenging or important. 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.

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 24, 2020 at 23:59 on the submission platform. This is a hard deadline.

Archives

About

Lectures for INFO8010 - Deep Learning, ULiège

License:BSD 3-Clause "New" or "Revised" License


Languages

Language:Jupyter Notebook 99.4%Language:TeX 0.2%Language:CSS 0.2%Language:Python 0.2%Language:HTML 0.0%