Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Thuy, Arthur"'
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 state-of-the-art performance, primarily through supervised methods but
Externí odkaz:
http://arxiv.org/abs/2409.09258
Autor:
Thuy, Arthur, Benoit, Dries F.
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-distribution (OOD) data. Worryingly, NNs tend to make confident yet i
Externí odkaz:
http://arxiv.org/abs/2403.10182
Autor:
Thuy, Arthur, Benoit, Dries F.
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 distribution shifts, where the model performance silently degrades as t
Externí odkaz:
http://arxiv.org/abs/2403.10168
Autor:
Thuy, Arthur, Benoit, Dries
Publikováno v:
EURO 2022 : conference handbook and abstracts : 32nd European Conference on Operational Research (EURO XXXII)
Recent successes across a variety of domains have led to the widespread deployment of neural networks in the field of operations research. Neural networks offer strong predictive performance but are notoriously difficult to interpret, leading to blac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______330::b18b2cfb6e11a3178c210adc955d2c2b
https://biblio.ugent.be/publication/01H5M95ZCPSK1WQS5DJYR7HDBZ
https://biblio.ugent.be/publication/01H5M95ZCPSK1WQS5DJYR7HDBZ