Menu

Advisory Board

Professor Hilbert J. Kappen

Hilbert J. Kappen, Ph.D. is Professor of Biophysics at Radboud University Nijmegen, the Netherlands.
 
Bert studied particle physics in Groningen, the Netherlands and completed his Ph.D. in this field in 1987 at the Rockefeller University in New York. From 1987 to 1989 he worked as a scientist at the Philips Research Laboratories in Eindhoven, the Netherlands. Since 1989, he has conducted research on neural networks at the laboratory for biophysics of the University of Nijmegen, the Netherlands. In 1997 he became associate professor and in 2004 he became full professor at this university.
 
His group consists of 10 people and is involved in research on machine learning (stochastic processes, learning algorithms, probabilistic reasoning and several applications in collaboration with industry) and computational neuroscience. His research was awarded in 1997 the prestigious national PIONEER research subsidy. In 1998, He cofounded the company Smart Research, which sells prediction software based on neural networks.
 
Bert has developed the medical diagnostic expert system called Promedas, which assists doctors in making accurate diagnosis of patients. Promedas is currently being commercialized through a new spin-off company. He is director of the Dutch Foundation for Neural Networks (SNN), which coordinates research on neural networks in the Netherlands. He organizes annual national conferences on machine learning and artificial intelligence. He is the author of approximately 120 publications.
 
Bert authored An introduction to stochastic control theory, path integrals, and reinforcement learning and coauthored Loop Corrected Belief Propagation, Sufficient Conditions for Convergence of the Sum—Product Algorithm, On Cavity Approximations for Graphical Models, Survey propagation at finite temperature: application to a Sourlas code as a toy model, On the properties of the Bethe approximation and loopy belief propagation on binary networks, Spin-glass phase transitions on real-world graphs, Effects of Fast Presynaptic Noise in Attractor Neural Networks, Improving Cox survival analysis with a neural-Bayesian approach, and Haplotype Inference in General Pedigrees using the Cluster Variation Method.
 
Watch An efficient approach to stochastic optimal control, Finite horizon exploration for path integral control problems, and A path integral approach to stochastic optimal control.