Description
Leader of the group Machine Learning: Peter Grünwald.
Our research group focuses on how computer programs can learn from and understand data, and then make useful predictions based on it. These algorithms integrate insights from various fields, including statistics, artificial intelligence and neuroscience.
Machine-learning applications are increasingly part of every aspect of life, from speech recognition on cell phones to illness prediction in healthcare. One common problem is extremely polluted data, for which no single model can provide adequate explanations. At CWI we address this issue with statistical machine learning based on combining predictions from different models and experts in order to achieve reliable conclusions.
We also study how networks of neurons in the brain process information, and how modern deep-learning methods can benefit from neuroscience. We develop novel neural networks, like Deep Adaptive Spiking Neural Networks, and also theoretical models of neural learning and information processing in biology. Applications of our work range from low-energy consumption neural machine learning to neuroprosthetics, to increased insight into the question of how the brain works.
News
CWI and INRIA use AI to better predict harmful solar storms
Extreme solar storms can have destructive effects on communications and electrical power grids. To improve space weather forecasting systems Mandar Chandorkar combined AI and data from space missions. He defends his thesis on 14 November.
The brain as a computer
On Wednesday 6 November 2019 Sander Bohte (CWI and UvA) will hold his inaugural lecture “the Brain as a computer” as a professor by special appointment of Cognitive Neurobiology.
Sander Bohté and Kees Oosterlee awarded with NWO Indo-Dutch funding
Sander Bohté (Machine Learning) and Kees Oosterlee (Scientific Computing) have been awarded with funding from NWO’s Indo-Dutch joint research programme for ICT.
Sander Bohté, professor by special appointment of Cognitive Neurobiology at UvA
Sander Bohté (1974) has been named professor by special appointment of Cognitive Neurobiology, specialising in Computational Neuroscience, at the University of Amsterdam (UvA)'s Faculty of Science. The chair was designated on behalf of the Science Plus Foundation (Stichting Bèta Plus). He will be combining his professorship with his position as senior researcher at CWI's Machine Learning group.
Members
Associated Members
Publications
-
Mhammedi, Z, Grünwald, P.D, & Guedj, B. (2019). PAC-Bayes Unexpected Bernstein Inequality. In Proceedings NeurIPS (Annual Conference on Neural Information Processing Systems).
-
Grünwald, P.D, & Roos, T. (2019). Minimum Description Length Revisited. Mathematics for industry.
-
van Ommen, M, Koolen-Wijkstra, W.M, & Grünwald, P.D. (2019). Efficient algorithms for minimax decisions under tree-structured incompleteness. In Lecture Notes in Computer Science/Lecture Notes in Artificial Intelligence (pp. 336–347). doi:10.1007/978-3-030-29765-7_28
-
ter Schure, J.A, & Grünwald, P.D. (2019). Accumulation Bias in meta-analysis: the need to consider time in error control [version 1; peer review: two approved]. F1000Research, 8. doi:10.12688/f1000research.19375.1
-
Grünwald, P.D, & Mehta, N.A. (2019). A Tight Excess Risk Bound via a Unified PAC-Bayesian-Rademacher-Shtarkov-MDL Complexity. In Proceedings ALT (Algorithmic Learning Theory).
-
Liu, S, Oosterlee, C.W, & Bohte, S.M. (2019). Pricing options and computing implied volatilities using neural networks. Risks, 7(1). doi:10.3390/risks7010016
-
Wagenmakers, E.-J, Love, J, Marsman, M, Jamil, T, Ly, A, Verhagen, J, … Morey, R.D. (2019). Bayesian inference for psychology. Part II: Example applications with JASP. Psychonomic Bulletin & Review, 25(1), 58–76. doi:10.3758/s13423-017-1323-7
-
Borovykh, A.I, Bohte, S.M, & Oosterlee, C.W. (2019). Dilated convolutional neural networks for time series forecasting. Journal of Computational Finance, 73–101. doi:10.21314/JCF.2019.358
-
ter Schure, J.A. (2019). Efficient accumulation of scientific knowledge, research waste and accumulation bias. ERCIM News, 116, 8–9.
-
Degenne, R.R.B.P, & Koolen-Wijkstra, W.M. (2019). Pure Exploration with Multiple Correct Answers. In Advances in meural information processing systems.
Software
Squint: Experimenting in Prediction with Expert Advice problems
Squint provides a codebase to perform numerical proof-of-concept experiments in learning theory, particularly in Prediction with Expert Advice problems, a core problem in learning theory.
Current projects with external funding
-
Efficient Deep Learning Platforms (eDLP)
-
Enabling Personalized Interventions (EPI)
-
Human Brain Project - SGA3 (HBP-SGA3)
-
Safe Bayesian Inference: A Theory of Misspecification based on Statistical Learning (SAFEBAYES)
-
Spiking Neural Networks research program
Related partners
-
Philips
-
KPMG
-
SURFsara B.V.
-
Technische Universiteit Eindhoven
-
Universiteit Twente
-
Universiteit van Amsterdam
-
Vrije Universiteit Amsterdam