Lukas
Investigating brains and machines
Investigating brains and machines
I am a PhD student in Machine Learning at TU Berlin and the Max Planck Institute for Human Cognitive and Brain Sciences. I work on representation learning for humans and deep neural networks (in low data regimes), mostly using ideas from probability theory and/or cognitive science. I am mainly advised by Klaus-Robert Müller and co-supervised by Martin Hebart. I am also part of a Research Collaboration with Google Brain, where I am advised by Simon Kornblith. Previously, I was a MSc student in IT & Cognition / Computer Science of Isabelle Augenstein, Johannes Bjerva, and Maria Barrett at the University of Copenhagen.
My research mainly revolves around representation learning. In particular, I work on robust representations and out-of-distribution generalization in low data regimes across different fields. In so doing, I use neural networks, approximate Bayesian methods (such as variational inference) and other approaches from probability theory. Wherever applicable, I additionally draw inspiration from the cognitive sciences. Mostly, however, I am debugging, examining model behaviour, using print statements, and contemplating why things are not working. Have a look at the publications section for more information about my work and interests. Feel free to reach out to me, if you believe our research intentions are aligned and you are keen to collaborate on a project.