About
I am a machine learning researcher at Qualcomm AI Research, Amsterdam. Previously I was a postdoc in Max Welling’s Philips group with the Amsterdam Machine Learning Lab (AMLAB) at the University of Amsterdam. I did my PhD at UCL in the Machine Vision Group with Gabriel J. Brostow and Dr. Clare Wilson FRCOphth. Before that I studied engineering at The University of Cambridge, and am a scholar of Sidney Sussex College.
My current research interests include equivariance and combinatorial optimization, while previously I have worked on uncertainty quantification, unsupervised representation learning, variational inference, normalizing flows, optimization, and medical imaging.
For the last two years I lectured a course in Bayesian Statistics for Machine Learning, and have been the lab manager for the Philips lab at the UvA. I am proud contributor to the UvA Inclusive AI Initiative, which seeks to promote diversity and inclusion in the academic AI world.
Latest News
- March 2021: I talked at ELLIS Symposium Workshop on Geometric Deep Learning for Medical Imaging on Equivariance - Trends and Challenges. Watch the video
- February 2021: I talked at IBM Research on Exploiting Symmetries for Deep Learning
- September 2020: I joined as a Staff Engineer at Qualcomm AI Research, Amsterdam.
- August 2020: I lectured at the Machine Learning Summer School-Indonesia.
- September 2019: Our paper Deep Scale-spaces: Equivariance Over Scale was accepted to NeurIPS 2019
- September 2018: I have begun lecturing a new course at the UvA on Probability Theory for Machine Learning
- June 2018: I talked at London Machine Learning Meetup on Understanding & Generalising the Convolution. Watch the video
Reading Groups
- UvA AMLAB Seminars
- UvA Geometric Methods: Riemannian Geometry Notes
- UCL Computer Vision Reading Group
Current Masters Students
Alessandra van Ree: Neural PDE Solvers
Previous Masters Students
Eli de Smet: Simple Saddle-Free Newton Descent with a Pseudo-Hessian
Jan Huiskes: FF-net: A fast Fourier transform inspired neural network
Rob Hesselink: Contrastive Learning of Equivariant Representations
Vivian van Oijen: Esophageal histopathology screening
Bryan Cardenas: Esophageal histopathology screening
Christina Winkler: Conditional Normalizing Flows
Nichita Diaconu: Learning convolutions
Jonas M J Braun: Non-geometric equivariance
Marios Fournarakis: Equivariance for tracking
Tycho van der Ouderaa: Reversible Networks for Memory-efficient Image-to-Image Translation in 3D Medical Imaging
Saki Shinoda: Semi-supervised learning