02901 Advanced Topics in Machine Learning: Self-Supervised Learning

August 21-25, 2023

Description

The course consists of five days (Monday-Friday, 9 AM - 4 PM) of lectures and exercises. The lectures will cover theoretical and practical aspects of Self-Supervised Learning. Technical aspects, programming and application of the developed concepts will be explored in tutorials and exercises. The course (2.5 ECTS points) is passed by handing in a small report on one of the topics covered in the course. For further course details click here.

Location

DTU building 303A auditorium 49 on Monday the 21st of August and building 324 room 040 during the 22nd-25th of August

Tentative Course Programme

Monday:

Lars Kai Hansen , Introduction/SSL cookbook
Kristoffer Wickstrøm, UiT The Arctic University of Norway, XAI for understanding of SSL representations
Exercise: XAI

Tuesday:

Alessio Ansuini & Alberto Cazzaniga, AREA Science Park, Italy, SSL Representations & Intrinsic dimension
Exercise: Intrinsic dimension

Wednesday:

Emanuele Rodolà, Sapienza University of Rome, Italy, Introduction to relative representations
Exercise: Relative dimension
Summer School Dinner at 6 PM

Thursday:

Anna Rogers, ITU, Denmark, SSL and NLP
Exercise: NLP
Sadaf Farkhani, DRCMR / DTU Compute, Vision Transformer in Healthcare: Harnessing the Power and Unraveling the Trade-offs

Friday:

Work on student presentations
Student presentations, wrap-up & goodbye

Requirements

General understanding of machine learning, statistical modeling, mathematics and computer science. Programming experience, ideally in Python. For the course you are required to bring your own laptop computer.