Tom Heskes
Intelligent Systems, Institute for Computing and Information Sciences
Radboud University Nijmegen,
Heyendaalseweg 135, 6525 AJ  Nijmegen
The Netherlands
Tel: 31-24-3652696
t.heskes@science.ru.nl
http://www.cs.ru.nl/~tomh


Career
 
 1984-1989: Masters Degree in Physics, Radboud University Nijmegen
               thesis on phase transitions in statistical physics
 1989-1993: PhD in Physics, Radboud University Nijmegen
               thesis on learning processes in neural networks
 1993-1994: Postdoc, Department of Physics and Beckman Institute,
            University of Illinois, Champaign-Urbana, USA
 1994-2004: Research assistant, SNN, Radboud University Nijmegen
 1998-2004: Director of SMART Research BV
 2001-2004: Assistant Professor Radboud University of Nijmegen, Physics
 2004-2007: Assistant Professor Radboud University Nijmegen, Computer Science
 2007-2008: Associate Professor Radboud University Nijmegen, Computer Science
 2007-    : Principal Investigator at the Institute for Computing and Information Sciences
            Affiliated Principal Investigator at the Donders Centre for Neuroscience
 2008-    : Full Professor Radboud University Nijmegen, Computer Science


Research interests

  - Bayesian machine learning (approximate inference, multi-task learning,
    dynamic Bayesian networks, preference elicitation, ...);
  - Applications to neuroimaging (brain-computer interfaces, fMRI analysis, ...)
    and bioinformatics (PPI networks, GWAS, ...)


Grants

  - SYNCOBE, NWO Complexity, 2010 (PhD student)
  - Learning2Reason, NWO Open, 2010 (PhD student)
  - GENEUSS, NWO Computational Life Sciences, 2007 (3 fte postdoc)
  - Braingain, SmartMix, 2007 (2 PhD students)
  - VICI, NWO, 2006 (1.25 MEuro)
  - Personalization of hearing aids, STW, 2006 (PhD student, 2.5 fte postdoc)
  - Bayesian brain-computer interfacing, STW, 2005 (4 fte postdoc)
  - AI4IA; Marie Curie Research Training Network, 2004 (PhD student)
  - Sales forecasting through aggregation, STW, 2000 (4 fte postdoc)
  - Graphical models for data mining, STW, 2000 (4 fte postdoc 1.5 fte programmer)
  - Neural networks in the paper industry, KCPK, 1999 (PhD student)


Professional activities

  - Editor-in-Chief of Neurocomputing
  - Associate Editor BMC Systems Biology, IEEE Transactions on Neural Networks,
    International Journal of Innovative Computing Information and Control,
    Foundations and Trends in Machine Learning, and
    International Journal of Computational Intelligence Systems
  - Organizer of BNAIC 2003 and PRIB 2010
  - Program committee member of (from 2004 onwards) ICANN 2008-2010, ECML/PKDD 2008,
    EvoBIO 2008-2011, Benelearn 2007-2010, ICMLC 2007-2010, IWANN 2007, 2009, 2011,
    IWINAC 2007, ESTSP 2007, IEEE ICEIS 2007, ICIC 2006, ANNPR 2006, 2008, 2010,
    AAAI06, SDM 2006, IDA 2005, ALaRT 2005, UAI 2005-2006, 2008-2009, PreMI 2005, 2007,
    IJCAI 2005, AISTATS 2005, 2009, ESANN 2004-2010, ICA 2004, 2006, BNAIC 2004-2010,
    ICML 2004, 2008-2011, EUNITE 2004, ICNC 2009-2010, EANN 2011, IEEE FOCI 2011,
    HAIS 2011, ICPRAM 2011, ICMMI 2011
  - Advisory/steering/senior program committee member of ISNN 2007, LSMS 2007, ICML 2007,
    UAI 2010-2011, ELM 2012
  - Member of STW Veni committee, 2010-2011, IWT jury, 2010, FWO expert panel



Some relevant/recent publications

Botond Cseke and Tom Heskes: "Approximate marginals in latent Gaussian models",
Journal of Machine Learning Research, 2:417-454, 2011.

Tom Claassen and Tom Heskes: "Causal discovery in multiple models from different
experiments", Advances in Neural Information Processing Systems 23, pp. 415-423, 2010.

Marcel van Gerven, Floris de Lange, and Tom Heskes: "Neural decoding with hierarchical
generative models", Neural Computation, 12:3127, 2010.

Ali Bahramisharif, Marcel van Gerven, Tom Heskes, and Ole Jensen: "Covert attention
allows for continuous control of brain-computer interfaces", European Journal of
Neuroscience, 31:1501, 2010.

Marcel van Gerven, Botond Cseke, Floris de Lange, and Tom Heskes, "Efficient Bayesian
multivariate fMRI analysis using a sparsifying spatio-temporal prior", Neuroimage,
50:150, 2010.

Marcel van Gerven, Christian Hesse, Ole Jensen, and Tom Heskes: "Interpreting single
trial data using groupwise regularisation", Neuroimage, 46:665, 2009.

Rasa Jurgelenaite, Tjeerd Dijkstra, Clemens Kocken, and Tom Heskes: "Gene regulation
in the intraerythrocytic cycle of Plasmodium Falciparum", Bioinformatics, 25:1484, 2009.

Rasa Jurgelenaite and Tom Heskes: "Learning symmetric causal independence models",
Machine Learning, 71:133, 2008.

Tom Heskes: "Convexity arguments for efficient minimization of the Bethe and
Kikuchi free energies", Journal of Artificial Intelligence Research, 26:153, 2006.

Tom Heskes: "On the uniqueness of loopy belief propagation fixed points",
Neural Computation, 16:2379, 2004.

Onno Zoeter and Tom Heskes: "Hierarchical visualization of time-series
data using switching linear dynamical systems", IEEE Transactions on
Pattern Analysis and Machine Intelligence, 25:1201, 2003.

Bart Bakker and Tom Heskes: "Task clustering and gating for Bayesian
multitask learning", Journal of Machine Learning Research, 4:83, 2003.

Tom Heskes, Kees Albers, and Bert Kappen: "Approximate inference and
constrained optimization", UAI2003, 2003.

Tom Heskes: "Stable fixed points of loopy belief propagation are local
minima of the Bethe free energy", NIPS 15, 2003.

Tom Heskes and Onno Zoeter: "Expectation propagation for approximate
inference in dynamic Bayesian networks", UAI2002, 2002.

Tom Heskes: "Self-organizing maps, vector quantization, and mixture modeling",
IEEE Transactions on Neural Networks, 12:1299, 2001.