Formal name: Dr. S.M. Bohte
Function: Scientific Staff Member
Email: S.M.Bohte@cwi.nl
Telephone +31(0)20 592 4074
Room: M244
Research groups:
(MAC4) Life sciences
Research
I develop computational models to help understand the mechanisms that underly information processing in networks of - mainly - spiking neurons. I have particularly focused on encoding information with timed spikes, supervised neural learning, and general reinforcement learning methods. Recently, we developed a straightforward neural spike coding and decoding framework, where we observe that a spiketrain can be the fractional derivative of a signal. This constitutes both a simple and elegant neural coding paradigm that can account for a number of experimental observations. With Pieter Roelfsema and Arjen van Ooyen, we work on biologically plausible policy gradient reinforcement learning in spiking neurons. Elaborating on the AGREL idea, the research is yielding some surprising results on the (in)sufficiency of standard policy-gradient reinforcement learning. Other machine learning efforts have focused on distributed learning paradigms, mainly within the Multi-Agent Learning paradigm, with such applications as hospital patient scheduling and energy distribution in smart grids.
Career
| 2010 - | Scientific staff member MAC4 - Life Sciences |
| 2002 - 2009 | Scientific staff member SEN4 - Multi-agent and Adaptive Computation |
| 1998 - 2002 | PhD student SEN4 - Multi-agent and Adaptive Computation |
Selected Awards and Honours
| 2004 | Veni Innovational Research Grant NWO |
Selected Academic Activities
| 2011 - 2012 | Guest lecturer Universiteit Leiden - [UL] - Lecturer Artificial Neural Networks |
| 2005 - 2008 | Lecturer Technische Universiteit Delft - [TUD] |
Selected Publications
| S.M. Bohte, J.O. Rombouts. Fractionally predictive spiking neurons. Advances in Neural Information Processing Systems 23, Vancouver, CA, USA, 253–261, 2010. |
| I.B. Vermeulen, S.M. Bohte, S.G. Elkhuizen, J.S. Lameris, P.J.M. Bakker, J.A. La Poutré. Adaptive resource allocation for efficient patient scheduling. Artificial Intelligence in Medicine 46, 67–80, 2009. |
| S.M. Bohte, M.C. Mozer. Reducing spike train variability: A computational theory of spike-timing dependent plasticity. Neural Computation 19, 371–403, 2007. |
| P.J. 't Hoen, S.M. Bohte, J.A. La Poutré. Learning from induced changes in opponent (re)actions in multi-agent games. Proceedings of the 5th International Joint Conference on Autonomous Agents and Multiagent Systems, Hakodate, Japan, 728–735, 2006. |
