nguyenducnhaty/info8010-deep-learning

Lectures for INFO8010 - Deep Learning, ULiège

INFO8010 - Deep Learning

Lectures for INFO8010 - Deep Learning, ULiège, Spring 2019.

• Instructor: Gilles Louppe ([email protected])
• Teaching assistants:
  • Joeri Hermans ([email protected])
  • Matthia Sabatelli ([email protected])
  • Antoine Wehenkel ([email protected])
• When: Spring 2019, Friday 9:00AM
• Classroom: B28/R7

Slides

• Outline [PDF]
• Lecture 1 (February 8): Fundamentals of machine learning [PDF]
• Lecture 2 (February 15): Neural networks [PDF]
• Lecture 3 (February 22): Convolutional neural networks [PDF]
• Lecture 4 (March 1): Training neural networks [PDF]
• Lecture 5 (March 8): Recurrent neural networks [PDF]
• Lecture 6 (March 15): Auto-encoders and generative models [PDF]
• Lecture 7 (March 29): Generative adversarial networks [PDF]
• Lecture 8 (April 5): Uncertainty [PDF]
• Lecture 9 (April 26): Adversarial attacks and defense [PDF]
• All lectures [PDF]

Project presentations:

• Lecture 10 (May 3): Student presentations 1
• Lecture 11 (May 10): Student presentations 2
• Lecture 12 (May 17): Student presentations 3

Tutorials

• Tutorial (March 8): Tensorflow [PDF]
• Tutorial (March 15): Pytorch [Notebook]

Project

See instructions in project.md.

Agenda

• Project proposal, due by March 1, 2019 at 23:59.
• Project code and report, due by May 1, 2019 at 23:59.
• Project presentations on May 3, 10 and 17, 2019.

Projects should be submitted through the Montefiore submission platform.

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:

• He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. arXiv:1512.03385.
• Andrychowicz, M., Denil, M., Gomez, S., Hoffman, M. W., Pfau, D., Schaul, T., ... & De Freitas, N. (2016). Learning to learn by gradient descent by gradient descent. arXiv:1606.04474.
• Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016). Understanding deep learning requires rethinking generalization. arXiv:1611.03530.

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 5, 2019 at 23:59 on the submission platform. This is a hard deadline.