Aasa Feragen

PhD, Associate Professor
Department of Computer Science (DIKU)
University of Copenhagen

Visiting address:
Universitetsparken 1
2100 København Ø
Denmark

Mail address:
Universitetsparken 5
2100 København Ø
Denmark

News

  • ICML workshop: Geometry in Machine Learning I will be co-organizing a workshop on Geometry in Machine Learning at ICML'18 in Stockholm, 13-15.7.2018. Stay tuned for more information!
    Sendt 3. apr. 2018 06.58 af Aasa Feragen
  • Two ISMRM abstracts accepted My previous BSc students Michael and Henrik are going to Paris: Their BSc thesis was accepted as an ISMRM abstract: Biases in classical structural parcellationMoreover, with my my postdoc ...
    Sendt 19. mar. 2018 05.21 af Aasa Feragen
  • CVPR paper by Anton Mallasto! Congratulations Anton! Our paper "Wrapped Gaussian Process Regression on Riemannian Manifolds" is going to appear at CVPR 2018!Check out the preprint here.
    Sendt 19. mar. 2018 01.54 af Aasa Feragen
  • NIPS area chair 2018 I am happy to serve as an area chair for NIPS 2018!
    Sendt 19. mar. 2018 01.51 af Aasa Feragen
  • Grant from Novo Nordisk Foundation Together with Pia Nyeng and Henrik Semb from Danstem, we have received a grant of 2.1 million from the Novo Nordisk foundation for the project "Quantifying the topological events ...
    Sendt 16. mar. 2018 08.05 af Aasa Feragen
Viser post 1 - 5 af 13. Vis flere »


SHORT BIO
I am a mathematician by training, and a mathematical modeller by heart.
My research focus is machine learning for medical imaging, in particular for geometrically constrained data.

My path here:
2014: Back at DIKU as Associate Professor
2012: Joined the MLCB group at the MPI for Intelligent Systems / MPI for Developmental Biology in Tübingen, to work on graph kernels
2009: Joined the Image Section at DIKU as postdoc, working with Francois and Mads on tree-shape analysis
2010: PhD in pure mathematics from the University of Helsinki with a thesis on singularity theory

RESEARCH INTERESTS
Uncertainty quantification for functional data in medical imaging
Statistics and machine learning for data with topological variation (trees, graphs, point sets, functions, images).
Nonlinear statistics; statistics in metric spaces such as Riemannian manifolds, stratified spaces, spaces of trees and graphs.
Applications in medical imaging and computer visison.