Zobrazeno 1 - 10
of 246
pro vyhledávání: '"Bell, Samuel"'
Growing experimental evidence shows that cell monolayers can induce long-lived perturbations to their environment, akin to footprints, which in turn influence the global dynamics of the system. Inspired by these observations, we propose a comprehensi
Externí odkaz:
http://arxiv.org/abs/2409.05195
Neural networks can fail when the data contains spurious correlations. To understand this phenomenon, researchers have proposed numerous spurious correlations benchmarks upon which to evaluate mitigation methods. However, we observe that these benchm
Externí odkaz:
http://arxiv.org/abs/2409.04188
Autor:
Lacroix, Mathilde, Smeets, Bart, Blanch-Mercader, Carlès, Bell, Samuel, Giuglaris, Caroline, Chen, Hsiang-Ying, Prost, Jacques, Silberzan, Pascal
Directed collective cell migration is central in morphogenesis, wound healing and cancer progression1,2. Although it is well-accepted that the molecular anisotropy of the micro-environment guides this migration3,4, its impact on the pattern of the ce
Externí odkaz:
http://arxiv.org/abs/2405.18807
Autor:
Hall, Melissa, Bell, Samuel J., Ross, Candace, Williams, Adina, Drozdzal, Michal, Soriano, Adriana Romero
Rapid progress in text-to-image generative models coupled with their deployment for visual content creation has magnified the importance of thoroughly evaluating their performance and identifying potential biases. In pursuit of models that generate i
Externí odkaz:
http://arxiv.org/abs/2405.04457
Autor:
Bell, Samuel J., Sagun, Levent
Which parts of a dataset will a given model find difficult? Recent work has shown that SGD-trained models have a bias towards simplicity, leading them to prioritize learning a majority class, or to rely upon harmful spurious correlations. Here, we sh
Externí odkaz:
http://arxiv.org/abs/2212.06641
Amid mounting concern about the reliability and credibility of machine learning research, we present a principled framework for making robust and generalizable claims: the multiverse analysis. Our framework builds upon the multiverse analysis (Steege
Externí odkaz:
http://arxiv.org/abs/2206.05985
Autor:
Bell, Samuel J., Lawrence, Neil D.
We investigate the effect of task ordering on continual learning performance. We conduct an extensive series of empirical experiments on synthetic and naturalistic datasets and show that reordering tasks significantly affects the amount of catastroph
Externí odkaz:
http://arxiv.org/abs/2205.13323
Cell monolayers are a central model system to tissue biophysics. In vivo, epithelial tissues are curved on the scale of microns, and curvature's role in the onset of spontaneous tissue flows is still not well-understood. Here, we present a hydrodynam
Externí odkaz:
http://arxiv.org/abs/2203.05644
Autor:
Bell, Samuel J., Lawrence, Neil D.
Publikováno v:
Presented at the AI Evaluation Beyond Metrics (EBeM) Workshop at IJCAI, Vienna 2022
In this paper we explore whether the fundamental tool of experimental psychology, the behavioral experiment, has the power to generate insight not only into humans and animals, but artificial systems too. We apply the techniques of experimental psych
Externí odkaz:
http://arxiv.org/abs/2110.10570
Autor:
Bell, Samuel J., Kampman, Onno P.
In the early 2010s, a crisis of reproducibility rocked the field of psychology. Following a period of reflection, the field has responded with radical reform of its scientific practices. More recently, similar questions about the reproducibility of m
Externí odkaz:
http://arxiv.org/abs/2104.08878