Deep Unlearn: Benchmarking Machine Unlearning

Autor: Cadet, Xavier F., Borovykh, Anastasia, Malekzadeh, Mohammad, Ahmadi-Abhari, Sara, Haddadi, Hamed

Machine unlearning (MU) aims to remove the influence of particular data points from the learnable parameters of a trained machine learning model. This is a crucial capability in light of data privacy requirements, trustworthiness, and safety in deplo

Externí odkaz: http://arxiv.org/abs/2410.01276

Evaluating The Robustness of Self-Supervised Representations to Background/Foreground Removal

Autor: Cadet, Xavier F., Aloufi, Ranya, Miranville, Alain, Ahmadi-Abhari, Sara, Haddadi, Hamed

Despite impressive empirical advances of SSL in solving various tasks, the problem of understanding and characterizing SSL representations learned from input data remains relatively under-explored. We provide a comparative analysis of how the represe

Externí odkaz: http://arxiv.org/abs/2306.01398

A Study on the Reliability of Automatic Dysarthric Speech Assessments

Autor: Cadet, Xavier F., Aloufi, Ranya, Ahmadi-Abhari, Sara, Haddadi, Hamed

Automating dysarthria assessments offers the opportunity to develop effective, low-cost tools that address the current limitations of manual and subjective assessments. Nonetheless, it is unclear whether current approaches rely on dysarthria-related

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::509db9afa4bebf4731530ff204c00729
http://arxiv.org/abs/2306.04337

Identification of flux checkpoints in a metabolic pathway through white-box, grey-box and black-box modeling approaches

Autor: Lo-Thong, Ophélie, Charton, Philippe, Cadet, Xavier F., Grondin-Perez, Brigitte, Saavedra, Emma, Damour, Cédric, Cadet, Frédéric

Publikováno v: Scientific Reports
Scientific Reports, Nature Publishing Group, 2020, 10 (1), pp.13446. ⟨10.1038/s41598-020-70295-5⟩
Scientific Reports, Nature Publishing Group, 2020, 10 (1), ⟨10.1038/s41598-020-70295-5⟩
Scientific Reports, 2020, 10 (1), pp.13446. ⟨10.1038/s41598-020-70295-5⟩
Scientific Reports, Vol 10, Iss 1, Pp 1-19 (2020)

International audience; Metabolic pathway modeling plays an increasing role in drug design by allowing better understanding of the underlying regulation and controlling networks in the metabolism of living organisms. However, despite rapid progress i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=pmid_dedup__::375125e8714184d6ec39019b1efb6fef
https://www.hal.inserm.fr/inserm-02946468/document

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.