Picture

Samuel Matthiesen

(née G. Fadel)

Postdoc Researcher, Technical University of Denmark

DTU Compute, Section for Cognitive Systems

About me

I am a postdoctoral researcher at the Technical University of Denmark, funded by the Danish Data Science Academy.

My main research interests are on unsupervised (or self-supervised) machine learning, particularly with geometrically-inspired representations. I investigate how the geometry of representations learned by different models can be either enforced or understood through the formalism of Riemannian manifolds.

These interests into a geometric perspective started during my PhD, where I worked on graph-based representations of data. For example, I investigated temporal graph-based recommender systems and a geometric take on latent representation interpolation in normalising flows using hyperspheres.

Prior to that, I focused on data (or information) visualization, with an emphasis on making high-dimensional data understandable through interactive two-dimensional scatterplots.

Teaching

Most of my teaching experience is at graduate (MSc. level) courses, but I have worked as a teaching assistant for BSc. courses.

When opportunity allows it, I also try to come up with alternative ways to help students understand some concepts. Particularly for a Deep Learning course, I have designed a visualization tool for convolutions. I would be happy to hear if you found it useful or have feedback.

Publications

Background