no code implementations • 25 Mar 2024 • Sondess Missaoui, Simos Gerasimou, Nikolaos Matragkas
Despite their unprecedented success, DNNs are notoriously fragile to small shifts in data distribution, demanding effective testing techniques that can assess their dependability.
no code implementations • 28 Jul 2023 • Kevin Denamganaï, Daniel Hernandez, Ozan Vardal, Sondess Missaoui, James Alfred Walker
We show that the referential game's agents make an artificial language emerge that is aligned with the natural-like language used to describe goals in the BabyAI benchmark and that it is expressive enough so as to also describe unsuccessful RL trajectories and thus provide feedback to the RL agent to leverage the linguistic, structured information contained in all trajectories.
no code implementations • 27 Apr 2023 • Kevin Denamganaï, Sondess Missaoui, James Alfred Walker
Natural languages are powerful tools wielded by human beings to communicate information.
1 code implementation • 16 Jul 2022 • Kevin Denamganaï, Sondess Missaoui, James Alfred Walker
Human beings use compositionality to generalise from past experiences to novel experiences.