SCHEDULE

PART 1: Learning representations (15:00 to 17:00)

The deep learning (DL) paradigm has been widely adopted in almost all domains of image analysis
as an alternative to traditional handcrafted techniques. However, the majority of deep neural
networks rely on the existence of significant amounts of training data that are not always
readily available.
– Why does modern machine learning require such large amounts of information/supervision?
– How do neural networks learn representations and what is representation learning?
– How representation learning relates to causality and the notion of generating factors?
– How disentangled representations related to generating factors and what are the standard
  methods to learn disentangled representations?

PART 2: Applications of disentangled representations in computer vision and medical imaging (17:15 to 19:00)

We discuss possible applications in computer vision and the medical imaging field and existing
open-ended challenges.
– What have been instrumental models solving image to image, segmentation and other tasks in computer vision?
– What have been ground breaking approaches in medical image analysis that can address challenges
  of data scarcity in medical imaging?
– What open challenges remain in the field of disentanglement?

Accompanying notes: https://arxiv.org/abs/2108.12043

BIO – Prof. Sotirios A. Tsaftaris, or Sotos, is currently the Canon Medical/Royal Academy of Engineering
Research Chair in Healthcare AI, and Chair (Full Professor) in Machine Learning and Computer Vision
at the University of Edinburgh (UK). He is also a Turing Fellow with the Alan Turing Institute. Previously
he held faculty positions with IMT Institute for Advanced Studies Lucca (Italy) and Northwestern University (USA).
He has published extensively, particularly in interdisciplinary fields, with more than 180 journal and conference
papers in his active record. His research interests are machine learning, computer vision, image analysis and processing.