Main sources of variability and non-determinism in AD software: taxonomy and prospects to handle them

M Alcon, A Brando, E Mezzetti, J Abella, FJ Cazorla - Real-Time Systems, 2023 - Springer
Safety standards in domains like automotive and avionics seek for deterministic execution
(lack of jittery behavior) as a stepping stone to build a certification argument on the correct …

Retrospective uncertainties for deep models using vine copulas

N Tagasovska, F Ozdemir… - … Conference on Artificial …, 2023 - proceedings.mlr.press
Despite the major progress of deep models as learning machines, uncertainty estimation
remains a major challenge. Existing solutions rely on modified loss functions or architectural …

Standardizing the probabilistic sources of uncertainty for the sake of safety deep learning

A Brando, I Serra, E Mezzetti… - Proceedings of the …, 2023 - upcommons.upc.edu
Nowadays, critical functionalities are increasingly tackled by autonomous decision-making
systems, which depend on Artificial Intelligence (eg Deep Learning) models. Still, most of …