PhD in Machine Learning, 2018
Delft University of Technology
MSc in Neuroscience, 2013
I am interested in robots, brains and robotbrains. I’m fascinated by intelligent behaviour: how animals can efficiently process a flood of sensory signals and learn to take actions that keep them alive. I’m passionate about taking what we know from how brains process information, to making intelligent machines.
My work in the lab revolves around improving the efficiency of the inference process. We aim to allow individual nodes in an agent’s factor graph to decide for themselves if they will communicate a signal forward, based on how much the message would reduce free energy.
Previous research includes studying the limits of generalizing to data from other distributions (domain adaptation) and model selection under covariate shift (cross-validation). Mainly, I designed and analyzed maximum-likelihood, minimax and minimum-variance estimators, which are applied to problems in image, signal and natural language processing.