2 papers
nlin.CD2026
Hierarchy of extreme-event predictability in turbulence revealed by machine learning
Yuxuan Yang, Chenyu Dong, Gianmarco Mengaldo
Extreme-event predictability in turbulence is strongly state dependent, yet event-by-event predictability horizons are difficult to quantify without access to governing equations o…
cs.LG2024
Evaluation of post-hoc interpretability methods in time-series classification
Hugues Turbé, Mina Bjelogrlic, Christian Lovis +1
Post-hoc interpretability methods are critical tools to explain neural-network results. Several post-hoc methods have emerged in recent years, but when applied to a given task, the…