40 citations · 60 across the 8 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Active Learning to Guide Labeling Efforts for Question Difficulty Estimation
Arthur Thuy, Ekaterina Loginova, Dries F. Benoit
In recent years, there has been a surge in research on Question Difficulty Estimation (QDE) using natural language processing techniques. Transformer-based neural networks achieve…
cs.LG2024★ 40 cited
Explainability through uncertainty: Trustworthy decision-making with neural networks
Arthur Thuy, Dries F. Benoit
Uncertainty is a key feature of any machine learning model and is particularly important in neural networks, which tend to be overconfident. This overconfidence is worrying under d…
cs.LG2024★ 6 cited
Fast and reliable uncertainty quantification with neural network ensembles for industrial image classification
Arthur Thuy, Dries F. Benoit
Image classification with neural networks (NNs) is widely used in industrial processes, situations where the model likely encounters unknown objects during deployment, i.e., out-of…