Email: S.M.Bohte [at] cwi [dot] nl Phone: tel. (+31) (0)20 592 4074 Mailing Address: Prof.dr. Sander M. Bohté CWI ML group Science Park 123 NL-1098XG Amsterdam The Netherlands
Research overview
NL:Ik werk aan neurale netwerk modellen met als doel te begrijpen hoe biologische neurale netwerken zoals het brein informatie verwerken en hoe deze kennis kan worden toegepast in nieuwe klassen van neurale netwerken.
I develop bio-inspired an biologically plausible neural networks. The challenge is to develop insights from neuroscience into usefully computing neural networks, and to bring machine learning insights into models of how neurons in the brain compute. I particularly focus on continuous-time neural information processing, where time is an explicit dimension of the problem domain. This includes networks of spiking neurons, models of attention, predictive coding, interactive neural cognition, supervised neural learning, and deep reinforcement learning methods.
- A key research interest is scaling spiking neural networks to high accuracy and large-scale networks. Recente work includes this paper in Nature Machine Intelligence and this this pre-print on large-scale efficient online learning. In the NWA ACT project we apply these insights to human-machine interaction for autonomous vehicles.
- In collaboration with Pieter Roelfsema at NIN, we work on biologically plausible deep learning based on the assumption that animals learn behavior through reinforcement learning. Ie "Brainprop".
- In more applied machine learning efforts, we work on the application of AI in computational physics (with Nikolaj Mucke, Benjamin Sanderse and Kees Oosterlee).
- I hold an appointment as a part-time professor of Computational Neuroscience at the University of Amsterdam and as a part-time professor of Bio-Inspired Deep Learning at the University of Groningen.
For MSc-thesis projects, due to limited advisory capacity, I give preference to select students from UvA and RUG. Potential projects have to align either (spiking) neural networks to biology, or explore learning in spiking neural networks (SNNs) in ML settings.