Tim Boudewijn Bakker

PhD candidate (advised by Herke van Hoof and Max Welling)
AMLab
Institute of Informatics
University of Amsterdam
Science Park, Lab 42, L4.04

 

Personal page   Google scholar   Github   Twitter  

I am a PhD student at the Amsterdam Machine Learning Lab (AMLab) with Herke van Hoof and Max Welling. My research focuses on active learning and active sensing. Other interests include AI alignment, everything Bayesian, and reinforcement learning.


Selected Publications

  1. ECML
    Learning objective-specific active learning strategies with Attentive Neural Processes
    Bakker, Tim, Hoof, Herke, and Welling, Max
    In Proceedings of the European Conference on Machine Learning Sep 2023
    PDF Code
  2. NeurIPS ReALML Workshop
    Active Learning Policies for Solving Inverse Problems
    Bakker, T., Hehn, T., Orekondy, T., Behboodi, A., and Massoli, F. Valerio
    In Neural Information Processing Systems Workshop on Adaptive Experimental Design and Active Learning in the Real World Dec 2023
    PDF
  3. NeurIPS Deep Inverse Workshop
    Switching policies for solving inverse problems
    Bakker, T., Massoli, F. Valerio, Hehn, T., Orekondy, T., and Behboodi, A.
    In Neural Information Processing Systems Workshop on Deep Learning and Inverse Problems Dec 2023
    PDF
  4. MIDL
    On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction
    Bakker, T., Muckley, M., Romero-Soriano, A., Drozdzal, M., and Pineda, L.
    In Proceedings of Machine Learning Research Jul 2022
    PDF Code
  5. UrbComp
    Back to Basics: Deep Reinforcement Learning in Traffic Signal Control
    Kanis, S., Samson, L., Bloembergen, D., and Bakker, T.
    The 10th International Workshop on Urban Computing Nov 2021
    PDF Code
  6. NeurIPS
    Experimental design for MRI by greedy policy search
    Bakker, T., Hoof, H., and Welling, Max
    In Advances in Neural Information Processing Systems 33 Dec 2020
    PDF Code