Leader of the group Machine Learning: Peter Grunwald.

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.



Current events

ML Seminar: Glenn Shafer (Rutgers Business School – Newark and New Brunswick)

  • 2018-12-17T11:00:00+01:00
  • 2018-12-17T12:00:00+01:00
December 17 Monday

Start: 2018-12-17 11:00:00+01:00 End: 2018-12-17 12:00:00+01:00

Room L016 at CWI, Science Park 123 in Amsterdam

Everyone is welcome to attend the ML seminar of Glenn Schafer ( Rutgers Business School – Newark and New Brunswick)

Title: Game-Theoretic Statistics
Fermat and Pascal’s two different methods for solving the problem of division lead to two different mathematical foundations for probability theory:  a measure-theoretic foundation that generalizes the method of counting cases used by Fermat, and a game-theoretic foundation that generalizes the method of backward recursion used by Pascal.  The game-theoretic foundation has flourished in recent decades, as documented by my forthcoming book with Vovk, Game-Theoretic Probability and Finance.  In this book’s formulation, probability typically involves three players, a player who offers betting rates (Forecaster), a player who tests the reliability of the forecaster by trying to multiply the capital he risks betting at these rates (Skeptic), and a player who decides the outcomes (Reality).

Game-theoretic statistics is less developed but appears to offer powerful and flexible resources for applications.  One way of using the
game between Forecaster, Skeptic, and Reality in applications is to suppose there are multiple Forecasters, each making forecasts according to a given probability model.  This makes the picture look like standard statistical modeling in the tradition of Karl Pearson and R. A. Fisher, but it is only one possibility.  In this talk, based on Chapter 10 of Game-Theoretic Probability and Finance, I will explore some other possibilities, drawing on examples from least squares, survival analysis, and quantum computing.


Associated Members



Current projects with external funding

  • Deep Spiking Vision: Better, Faster, Cheaper (DEVIS)
  • Efficient Deep Learning Platforms (eDLP)
  • Enabling Personalized Interventions (EPI)
  • Safe Bayesian Inference: A Theory of Misspecification based on Statistical Learning (SAFEBAYES)

Related partners

  • Philips
  • KPMG
  • SURFsara B.V.
  • Universiteit van Amsterdam
  • Vrije Universiteit Amsterdam