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.
Vacancies
No vacancies currently.
News
ERCIM News 107 on Machine Learning co-coordinated by Sander Bohte - extra Open Access section
In October 2016, ERCIM News No. 107 was published: http://ercim-news.ercim.eu/en107. It features a special theme on current trends and new paradigms in Machine Learning, coordinated by the guest editors Sander Bohte (CWI ) and Hung Son Nguyen (University of Warsaw).
Bayesian statistics not as robust as commonly thought
The widely used method of Bayesian statistics is not as robust as commonly thought. Researcher Thijs van Ommen of Centrum Wiskunde & Informatica (CWI) discovered that for certain types of problems, Bayesian statistics finds non-existing patterns in the data. Van Ommen defends his thesis on this topic on Wednesday 10 June at Leiden University.
Researchers develop neural model for working memory
Neuroscientists of Centrum Wiskunde & Informatica (CWI) and the Netherlands Institute for Neuroscience (NIN) have developed a biologically plausible neural network model that can learn to remember past events in order to use them in the future. The researchers developed their model by combining theoretical principles from machine learning with insights from neuroscience.
CWI starts research on spiking neural networks
Sander Bohte, researcher in the life science group of the Centrum Wiskunde & Informatica (CWI) in Amsterdam, starts in collaboration with researchers from the University of Amsterdam (UvA) a new project on spiking neural networks.
Current events
Neuromorphic Computing Netherlands (NCN2021)
- 2021-09-24T12:50:00+02:00
- 2021-09-24T18:00:00+02:00
Neuromorphic Computing Netherlands (NCN2021)
Start: 2021-09-24 12:50:00+02:00 End: 2021-09-24 18:00:00+02:00
Neuromorphic Computing is rapidly emerging as the principle paradigm for EdgeAI. In this workshop, we aim to bring together researchers and practitioners from algorithmic, architectural and application domains in the Netherlands.
When: 24 September, 12:50h-17:30h.
Location: CWI Amsterdam and online (hybrid).
Keynote: prof dr Elisabetta Chicca (RUG)
Zoom link:
https://cwi-nl.zoom.us/j/86293297870?pwd=aWR0alphM1A0MHFXNWUySFRVanI4QT09
Program:
12:50h Opening
13:00h Keynote by Elisabetta Chicca (RUG)
13:50h break
14:00h Federico Corradi (IMEC)
14:25h Jesse Hagenaars (TUD)
14:50h Mahyar Shahsavari (RU)
15:15h posters / break
16:00h Bojian Yin (CWI)
16:25h Thomas Tiotto (RUG)
16:50h drinks
This workshop is organized as part of the Efficient Deep Learning NWO-TTW Perspectief programme.
- Email: Sander.Bohte@cwi.nl
-
iCal
Members
Associated Members
Publications
-
Sterkenburg, T.F, & Grünwald, P.D. (2021). The no-free-lunch theorems of supervised learning. Synthese. doi:10.1007/s11229-021-03233-1
-
Kruijne, W, Bohte, S.M, Roelfsema, P.R, & Olivers, C.N.L. (2021). Flexible working memory through selective gating and attentional tagging. Neural Computation, 33(1), 1–40. doi:10.1162/neco_a_01339
-
van Gendt, M.J, Siebrecht, M, Briaire, J.J, Bohte, S.M, & Frijns, J.H.M. (2020). Short and long-term adaptation in the auditory nerve stimulated with high-rate electrical pulse trains are better described by a power law. Hearing Research, 398. doi:10.1016/j.heares.2020.108090
-
Degenne, R.R.B.P, Shao, H, & Koolen-Wijkstra, W.M. (2020). Structure adaptive algorithms for stochastic bandits. In Proceedings of the International Conference on Machine Learning (pp. 2443–2452).
-
Mhammedi, Z, & Koolen-Wijkstra, W.M. (2020). Lipschitz and comparator-norm adaptivity in online learning. In Proceedings of Machine Learning Research (pp. 2858–2887).
-
Turner, R.J. (2020). Safe Statistics for Means and Proportions.
-
Grünwald, P.D, & Mehta, N.A. (2020). Fast rates for general unbounded loss functions: From ERM to generalized bayes. Journal of Machine Learning Research, 21, 1–80.
-
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
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)
-
Efficient Models of Decision-Making for Asseing Cognitive Processing States (None)
-
Perceptive acting under uncertainty: safety solutions for autonomous systems (None)
-
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