1 code implementation • 8 Nov 2019 • Vincent Ballet, Xavier Renard, Jonathan Aigrain, Thibault Laugel, Pascal Frossard, Marcin Detyniecki
Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions.
no code implementations • 25 Sep 2019 • Jonathan Aigrain, Marcin Detyniecki
Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a prediction with a reliable confidence estimate which would allow to detect misclassifications.
no code implementations • 4 Jun 2019 • Xavier Renard, Nicolas Woloszko, Jonathan Aigrain, Marcin Detyniecki
Interpretable surrogates of black-box predictors trained on high-dimensional tabular datasets can struggle to generate comprehensible explanations in the presence of correlated variables.
1 code implementation • 22 May 2019 • Jonathan Aigrain, Marcin Detyniecki
Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications.