Zobrazeno 1 - 10
of 1 184
pro vyhledávání: '"A, Zhioua"'
Autor:
Makhlouf, Karima, Arcolezi, Heber H., Zhioua, Sami, Brahim, Ghassen Ben, Palamidessi, Catuscia
Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the appropriate u
Externí odkaz:
http://arxiv.org/abs/2312.04404
Accurately measuring discrimination in machine learning-based automated decision systems is required to address the vital issue of fairness between subpopulations and/or individuals. Any bias in measuring discrimination can lead to either amplificati
Externí odkaz:
http://arxiv.org/abs/2310.13364
Autor:
Zhioua, Sami, Binkytė, Rūta
Accurately measuring discrimination is crucial to faithfully assessing fairness of trained machine learning (ML) models. Any bias in measuring discrimination leads to either amplification or underestimation of the existing disparity. Several sources
Externí odkaz:
http://arxiv.org/abs/2306.05068
Autor:
Pilar Junier, Guillaume Cailleau, Mathilda Fatton, Pauline Udriet, Isha Hashmi, Danae Bregnard, Andrea Corona-Ramirez, Eva di Francesco, Thierry Kuhn, Naïma Mangia, Sami Zhioua, Daniel Hunkeler, Saskia Bindschedler, Simon Sieber, Diego Gonzalez
Publikováno v:
Water Research X, Vol 24, Iss , Pp 100252- (2024)
Over the last two decades, proliferations of benthic cyanobacteria producing derivatives of anatoxin-a have been reported in rivers worldwide. Here, we follow up on such a toxigenic event happening in the Areuse river in Switzerland and investigate t
Externí odkaz:
https://doaj.org/article/d4f58f3984f94cb0ab76f37d204475f3
Autor:
Alves, Guilherme, Bernier, Fabien, Couceiro, Miguel, Makhlouf, Karima, Palamidessi, Catuscia, Zhioua, Sami
Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting with the hope of replacing subjective human decisions with objective machine learning (ML) algorithms. However, ML-based
Externí odkaz:
http://arxiv.org/abs/2209.13012
Besides its common use cases in epidemiology, political, and social sciences, causality turns out to be crucial in evaluating the fairness of automated decisions, both in a legal and everyday sense. We provide arguments and examples, of why causality
Externí odkaz:
http://arxiv.org/abs/2207.04053
Autor:
Binkytė-Sadauskienė, Rūta, Makhlouf, Karima, Pinzón, Carlos, Zhioua, Sami, Palamidessi, Catuscia
It is crucial to consider the social and ethical consequences of AI and ML based decisions for the safe and acceptable use of these emerging technologies. Fairness, in particular, guarantees that the ML decisions do not result in discrimination again
Externí odkaz:
http://arxiv.org/abs/2206.06685
Publikováno v:
American Journal of Ophthalmology Case Reports, Vol 33, Iss , Pp 101961- (2024)
Purpose: To report a case of peripapillary pachychoroid syndrome (PPS) complicated with peripapillary retinal neovascularization causing vitreous hemorrhage. Observation: A 42-year-old man, with a history of a visual loss of the right eye (RE) for 4
Externí odkaz:
https://doaj.org/article/d81c87a6a0904120bfcca427bff2776c
Machine learning algorithms can produce biased outcome/prediction, typically, against minorities and under-represented sub-populations. Therefore, fairness is emerging as an important requirement for the large scale application of machine learning ba
Externí odkaz:
http://arxiv.org/abs/2203.05900
Publikováno v:
In Journal of Logical and Algebraic Methods in Programming October 2024 141