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

Sander Bohté, professor by special appointment of Cognitive Neurobiology at UvA

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.

Sander Bohté, professor by special appointment of Cognitive Neurobiology at UvA - Read More…

CWI participates in new NWO Perspectief programme

CWI participates in new NWO Perspectief programme

In the coming years almost a hundred researchers are going to develop innovative technologies together with industry and social organisations. That will happen in six new Perspectief programmes, which have been given the green light by NWO, Netherlands Organisation for Scientific Research, on 21 November 2017. CWI's Machine Learning group participates in the programme Efficient Deep Learning Systems.

CWI participates in new NWO Perspectief programme - Read More…

Current events

ML Seminar: Yasin Abbasi (VinAI Research)

  • 2019-09-17T11:00:00+02:00
  • 2019-09-17T12:00:00+02:00
September 17 Tuesday

Start: 2019-09-17 11:00:00+02:00 End: 2019-09-17 12:00:00+02:00

Room L016 at CWI, Science Park 123 in Amsterdam

Everyone is welcome to attend the ML seminar of Yasin Abbasi with the title 'Efficient exploration in sequential decision making problems'.

Abstract: I will discuss recent results in designing more adaptive bandit algorithms. Our first approach is based on the bootstrap method and leads to a more efficient and data-dependent algorithm for the multi-armed bandit problem. Our second approach is a model-selection method for bandit problems. As an example of the usefulness of the approach, when the reward function is largely independent of the contexts, the method will automatically converge to the simpler and more efficient non-contextual algorithm.

ML Seminar: Alexander Marx (International Max Planck Research School for Informatics)

  • 2019-10-10T11:00:00+02:00
  • 2019-10-10T12:00:00+02:00
October 10 Thursday

Start: 2019-10-10 11:00:00+02:00 End: 2019-10-10 12:00:00+02:00

Room L016 at CWI, Science Park 123 in Amsterdam

Everyone is welcome to attend de ML seminar of Alexander Marx with the title 'Testing Conditional Independence on Discrete Data using Stochastic Complexity'.

Abstract: Testing for conditional independence is a core aspect of constraint-based causal discovery. Although commonly used tests are
perfect in theory, they often fail to reject independence in practice, especially when conditioning on multiple variables.
We focus on discrete data and propose a new test based on the notion of algorithmic independence that we instantiate using stochastic
complexity. Amongst others, we show that our proposed test, SCI, is an asymptotically unbiased as well as L2 consistent estimator for
conditional mutual information (CMI). Further, we show that SCI can be reformulated to find a sensible threshold for CMI that works well on limited samples. Empirical evaluation shows that SCI has a lower type II error than commonly used tests. As a result, we obtain a higher recall when we use SCI in causal discovery algorithms, without compromising the precision.

ML Seminar: Alexander Marx

  • 2019-10-10T11:00:00+02:00
  • 2019-10-10T12:00:00+02:00
October 10 Thursday

Start: 2019-10-10 11:00:00+02:00 End: 2019-10-10 12:00:00+02:00

Room L016 at CWI, Science Park 123 in Amsterdam

Everyone is welcome to attend the ML seminar of Alexander Marx with the title 'Testing Conditional Independence on Discrete Data using Stochastic Complexity'.

Abstract: Testing for conditional independence is a core aspect of constraint-based causal discovery. Although commonly used tests are perfect in theory, they often fail to reject independence in practice, especially when conditioning on multiple variables.
We focus on discrete data and propose a new test based on the notion of algorithmic independence that we instantiate using stochastic complexity. Amongst others, we show that our proposed test, SCI, is an asymptotically unbiased as well as L2 consistent estimator for conditional mutual information (CMI). Further, we show that SCI can be reformulated to find a sensible threshold for CMI that works well on limited samples. Empirical evaluation shows that SCI has a lower type II error than commonly used tests. As a result, we obtain a higher recall when we use SCI in causal discovery algorithms, without compromising the precision.

 

Members

Associated Members

Publications

Software

Current projects with external funding

  • Efficient Deep Learning Platforms (eDLP)
  • Enabling Personalized Interventions (EPI)
  • 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