20 citations · 20 across the 3 of their papers we have counts for
3 papers
PRIVET: PRoximIty leakage detection Via Extreme value Theory
Antoine Szatkownik, Aurélien Decelle, Beatriz Seoane +7
Deep generative models are often trained on sensitive data, such as genetic sequences, health data, or more broadly, any copyrighted, licensed or protected content. This raises cri…
Causal Analysis for Robust Interpretability of Neural Networks
Ola Ahmad, Nicolas Bereux, Loïc Baret +2
Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on corr…
Learning a Restricted Boltzmann Machine using biased Monte Carlo sampling
Nicolas Béreux, Aurélien Decelle, Cyril Furtlehner +1
Restricted Boltzmann Machines are simple and powerful generative models that can encode any complex dataset. Despite all their advantages, in practice the trainings are often unsta…