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.



No vacancies currently.


Current events

Paradiso lecture Sander Bohte

  • 2022-06-19T11:00:00+02:00
  • 2022-06-19T12:00:00+02:00
June 19 Sunday

Start: 2022-06-19 11:00:00+02:00 End: 2022-06-19 12:00:00+02:00

Paradiso, Weteringschans 6, 1017 SG Amsterdam

Kijken in de ziel van AI - Over het brein als computer

Moderne Artificial Intelligence (AI) is sterk geïnspireerd op het functioneren van het brein. Maar hoe werkt het brein eigenlijk? Of, preciezer, hoe is ons brein in staat om intelligent gedrag te genereren? En wat bedoelen we eigenlijk met ‘intelligent gedrag’? In zijn Paradisolezing gaat Sander in op de vraag hoe de honderden miljarden cellen in ons brein in staat zijn om intelligent gedrag te leren en uit te voeren. Hij legt de overeenkomsten met een computer uit, maar gaat ook in op de verschillen en hoe deze verschillen nieuwe inzichten bieden voor slimmere AI en energiezuinigere computers.


Please note that the Paradiso lectures are in Dutch.

Modern Artificial Intelligence (AI) is heavily inspired by the functioning of the brain. But how does the brain actually work? Or, more precisely, how is our brain able to generate intelligent behavior? And what do we actually mean by "intelligent behavior"? In his Paradiso Lecture, Sander addresses the question of how the hundreds of billions of cells in our brain are able to learn and execute intelligent behavior. He explains the similarities to a computer, but also discusses the differences and how these differences offer new insights for smarter AI and more energy-efficient computers.



Associated Members



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)

Related partners

  • Katholieke Universiteit Nijmegen
  • Philips
  • KPMG
  • SURFsara B.V.
  • Technische Universiteit Eindhoven
  • Technische Universiteit Delft
  • Universiteit Twente
  • Universiteit van Amsterdam
  • Vrije Universiteit Amsterdam