Doctoral course - Self-Supervised Learning for Multimodal Data: From Models to Loss Functions
Event information
Time
-
Location
TS127
External teacher(s): Zheng-Hua Tan
External teacher(s) organization: Aalborg University
ECTS -credits: 2
Grade: Pass or Fail
Assessment: oral exam after all lectures and research report within four weeks after lectures.
Lecture hall TS127
(Estimated) Date of the course *May 15-17, 2023
May 15, 9-11, Monday afternoon: Lecture 1
May 16, 9-11, Tuesday morning: Lecture 2
May 16, 13-15, Tuesday afternoon: Lecture 3
May 17, 9-11, Wed. morning: Lecture 4
May 17, 13-16, Wed. afternoon: Oral exam
Learning objectives and contents:
The course gives an introduction to self-supervised learning methods for learning representations of single- and multiple-modality data, covering deep architectures, training target and loss functions used in state-of-the-art methods, and selected downstream applications. A focus will be given to loss functions including both contrastive and predictive losses. The course will be taught through a combination of lectures and mini-projects.
Tentative topics:
Self-supervised learning concept and history
Deep learning architectures
Key methods: training target and loss functions
Applications
Amount of contact teaching hours *8 hours lecture