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.
I develop computational models to understand information processing in neural networks. I strongly believe that neural networks and computational neuroscience models should "compute"; 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 focused on continuous-time 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 work on neural adaptation and predictive coding for optimal spiking information processing. An example is the notion of multiplicative adaptation for adaptive spike coding, which allows spiking neurons to efficiently encode analog signals over vastly different and rapidly changing dynamic ranges. Current work focuses framing such adaptation in terms of predictive coding, and applying this paradigm to standard learning theory.
- We also work on biologically plausible policy gradient reinforcement learning of working memory, for so called Semi-Markov Decision Processes. In AuGMent, we show how synaptic tags combined with integrating neurons allow neural networks to learn sequences of tasks, closely mimicking the way monkeys learn these tasks. Recent work has shown how we can formulate learning and processing in RNNs like AuGMent in continuous-time, and implement this in spiking neural networks.
- Other research relates to neural models of early vision and audition, where the dynamic properties of real neurons are crucial to understanding the relationship between spiking and neural information processing.
- I have an appointment as a part-time full professor of Computational Neuroscience at the Swammerdam Institute for Life Sciences (SILS) of the University of Amsterdam and as a part-time full professor of Bio-Inspired Deep Learning at the Faculty of Science and Engineering of the University of Groningen. Active collaborations include work with Cyriel Pennartz (UvA); Pieter Roelfsema, at NIN Amsterdam; Steven Scholte at B&C, UvA and Margriet van Gendt, at LUMC Leiden.
- In more applied machine learning efforts, we work on the use of deep neural network models in finance (with Kees Oosterlee in the CWI Stochastics group).
Talented students are always welcome to come and do their MSc-thesis work at CWI on NeuroInformatics, either based on their own proposed ideas, or based some ready-made potential MSc thesis projects. In particular for projects that link (spiking) neural networks to biology, and also on work that explores (probabilistic) learning in spiking neural networks (SNNs), for example in connection with reservoir computing, or in projects on efficiently simulating large-scale SNNs, with for example GPUs. Feel free to contact me for more information.