Bert Kappen

15:00 - 16:15 - session: Artificial intelligence

Bert Kappen completed his PhD in theoretical particle physics in 1987 at the Rockefeller University in New York. From 1987 until 1989 he worked as a scientist at the Philips Research Laboratories in Eindhoven, the Netherlands.

Since 1989, he is conducting research on neural networks, Bayesian machine learning, stochastic control theory and computational neuroscience. His research has made significant contributions to approximate inference in machine learning using methods from statistical physics; he has pioneerd the field of path integral control methods for solving large non-linear stochastic optimal control problems and their relation to statistical physics.

Currently, he is interested in quantum machine learning and the realisation of learning in dedicated hardware. In 1997, his research was awarded the prestigious national PIONIER research subsidy from NWO/STW.

Since 1997 he is associate professor and since 2004 full professor at the Radboud University. In 2005 he was Miller visiting professor at the University of California at Berkeley. Since 2009, he is honorary faculty at UCL's Gatsby Computational Neuroscience Unit in London.

He co-founded in 1998 the company Smart Research that commercializes applications of neural networks and machine learning. Smart Research has developed forensic software for DNA matching used by the Dutch Forensic institute (MH17 plane crash over Ukraine in 2014), Interpol, the Vietnam government for analysis of victims of the Vietnam war and the Australian Police force. He is director of the Dutch Foundation for Neural Networks (SNN), which coordinates research on neural networks and machine learning in the Netherlands through the Machine Learning Platform.

Medical diagnostic decision support

Diagnostic errors are the most common, most costly and most dangerous of medical mistakes (BMJ 2013). Using computers to improve the accuracy and efficiency of the diagnostic process has been proposed long ago. However, up to today, the solutions have not been sufficiently successfull and are only few systems used in practice. The reasons are lack of high quality medical data and the computational complexity to compute a differential diagnosis. I will review these issues based on our experience with the Promedas system that was developed between 1998 and 2008. I conclude that despite all the past failures, Bayesian networks remain a very promising approach for computer assisted medical decision support.