247 citations · 247 across the 1 of their papers we have counts for
6 papers
The Data Representativeness Criterion: Predicting the Performance of Supervised Classification Based on Data Set Similarity
Evelien Schat, Rens van de Schoot, Wouter M. Kouw +2
In a broad range of fields it may be desirable to reuse a supervised classification algorithm and apply it to a new data set. However, generalization of such an algorithm and thus…
Back to the Future -- Sequential Alignment of Text Representations
Johannes Bjerva, Wouter Kouw, Isabelle Augenstein
Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural n…
A cross-center smoothness prior for variational Bayesian brain tissue segmentation
Wouter M. Kouw, Silas N. Ørting, Jens Petersen +2
Suppose one is faced with the challenge of tissue segmentation in MR images, without annotators at their center to provide labeled training data. One option is to go to another med…
An introduction to domain adaptation and transfer learning
Wouter M. Kouw, Marco Loog
In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new sampl…
Learning an MR acquisition-invariant representation using Siamese neural networks
Wouter M. Kouw, Marco Loog, Wilbert Bartels +1
Generalization of voxelwise classifiers is hampered by differences between MRI-scanners, e.g. different acquisition protocols and field strengths. To address this limitation, we pr…
Effects of sampling skewness of the importance-weighted risk estimator on model selection
Wouter M. Kouw, Marco Loog
Importance-weighting is a popular and well-researched technique for dealing with sample selection bias and covariate shift. It has desirable characteristics such as unbiasedness, c…