Research Output per year
Personal profile
Research profile
I am interested in robots, brains and robotbrains. Intelligent behaviour fascinates me: how animals can efficiently process a flood of sensory signals and learn to take actions to survive. I am passionate about taking lessons learned from how brains process information, to making intelligent machines.
My work in the Bayesian Intelligent Autonomous Systems lab focuses on making active inference agents more efficient. Our first steps consists of making individual nodes in factor graphs decide for themselves if they will communicate a signal forward, based on how much the message reduces free energy.
Previous projects include domain-adaptive machine learning and model validation under covariate shift. Mainly, I designed and analyzed maximum-likelihood and minimax estimators for statistical models, which have been applied to image, signal and natural language processing problems.
Education/Academic qualification
Doctor, Delft University of Technology
1 Sep 2013 → 31 Aug 2017
Master, Maastricht University
1 Sep 2011 → 31 Aug 2013
Network
Recent external collaboration on country level. Dive into details by clicking on the dots.
Research Output 2016 2019
A cross-center smoothness prior for variational Bayesian brain tissue segmentation
Kouw, W. M., Ørting, S. N., Petersen, J., Pedersen, K. S. & de Bruijne, M., 1 Jan 2019, International Conference on Information Processing in Medical Imaging. Bao, S., Chung, A. C. S., Gee, J. C. & Yushkevich, P. A. (eds.). Cham: Springer, p. 360-371 12 p. (Lecture Notes in Computer Science; vol. 11492 LNCS)Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
Open Access
File
Brain
Tissue
Classifiers
A review of domain adaptation without target labels
Kouw, W. M. & Loog, M., 7 Oct 2019, In : IEEE Transactions on Pattern Analysis and Machine Intelligence.Research output: Contribution to journal › Article › Academic › peer-review
Open Access
File
Labels
Classifiers
Target
Parameter estimation
Learning systems
Learning an MR acquisition-invariant representation using Siamese neural networks
Kouw, W. M., Loog, M., Bartels, L. W. & Mendrik, A. M., Jul 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). Piscataway: Institute of Electrical and Electronics Engineers, p. 364-367 4 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
Open Access
File
Classifiers
Neural networks
Magnetic resonance imaging
Tissue
Experiments
CT image segmentation of bone for medical additive manufacturing using a convolutional neural network
Minnema, J., van Eijnatten, M., Kouw, W., Diblen, F., Mendrik, A. & Wolff, J., 1 Dec 2018, In : Computers in Biology and Medicine. 103, p. 130-139 10 p.Research output: Contribution to journal › Article › Academic › peer-review
3D printers
Image segmentation
Tomography
Bone
Neural networks
Effects of sampling skewness of the importance-weighted risk estimator on model selection
Kouw, W. & Loog, M., 26 Nov 2018, International Conference on Pattern Recognition. Piscataway: Institute of Electrical and Electronics Engineers, p. 1468-1473 6 p. 8546186Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
Open Access
Sampling
Computational complexity
Prizes
Niels Stensen Fellow
Wouter Kouw (Recipient), Oct 2017
Recognition: Other › Fellowships & memberships › Scientific
university
experience