no code implementations • 21 Aug 2023 • Aymene Mohammed Bouayed, Adrian Iaccovelli, David Naccache
Furthermore, when it comes to generating images of faces and ocular images, our approach showcases substantial enhancements with FID improvements of $1. 69$ and $0. 87$ respectively, as compared to GMM sampling, as evidenced on the CelebA and MOBIUS datasets.
no code implementations • 16 Jan 2023 • Aymene Mohammed Bouayed, David Naccache
In this work, we propose a new approach that models the latent space of an Autoencoder as a simplex, allowing for a novel heuristic for determining the number of components in the mixture model.
no code implementations • 21 Dec 2022 • David Naccache, Ofer Yifrach-Stav
We provide the results of pattern recognition experiments on mathematical expressions.
1 code implementation • 30 Sep 2022 • Hadrien Barral, Georges-Axel Jaloyan, Fabien Thomas-Brans, Matthieu Regnery, Rémi Géraud-Stewart, Thibaut Heckmann, Thomas Souvignet, David Naccache
This paper provides a detailed explanation of the steps taken to extract and repair a Google Home's internal data.
no code implementations • 27 May 2022 • Adnan Ben Mansour, Gaia Carenini, Alexandre Duplessis, David Naccache
To date, the most popular federated learning algorithms use coordinate-wise averaging of the model parameters.
no code implementations • 22 May 2022 • Adnan Ben Mansour, Gaia Carenini, Alexandre Duplessis, David Naccache
The resulting model is then redistributed to clients for further training.
no code implementations • 18 Oct 2021 • Gaëlle Candel, David Naccache
Ensemble learning methods are naturally resilient to the absence of several peers thanks to the ensemble redundancy.
no code implementations • 14 Oct 2021 • Gaëlle Candel, David Naccache
Tags are short sequences of words allowing to describe textual and non-texual resources such as as music, image or book.
1 code implementation • 30 Sep 2021 • Antoine Scardigli, Paul Fournier, Matteo Vilucchio, David Naccache
HyperParameter Optimization (HPO) aims at finding the best HyperParameters (HPs) of learning models, such as neural networks, in the fastest and most efficient way possible.
no code implementations • 22 Sep 2021 • Gaëlle Candel, David Naccache
$t$-SNE is an embedding method that the data science community has widely Two interesting characteristics of t-SNE are the structure preservation property and the answer to the crowding problem, where all neighbors in high dimensional space cannot be represented correctly in low dimensional space.
no code implementations • 21 Sep 2021 • Gaëlle Candel, David Naccache
Bibliographic and co-citation coupling are two analytical methods widely used to measure the degree of similarity between scientific papers.
no code implementations • 15 Sep 2021 • Gaëlle Candel, David Naccache
Many datasets take the form of a bipartite graph where two types of nodes are connected by relationships, like the movies watched by a user or the tags associated with a file.
no code implementations • 6 May 2020 • Marc Beunardeau, Éric Brier, Noémie Cartier, Aisling Connolly, Nathanaël Courant, Rémi Géraud-Stewart, David Naccache, Ofer Yifrach-Stav
This paper describes how to optimally detect infected patients in pools, i. e. using a minimal number of tests to precisely identify them, given the a priori probabilities that each of the patients is healthy.
no code implementations • 11 Aug 2016 • Hadrien Barral, Houda Ferradi, Rémi Géraud, Georges-Axel Jaloyan, David Naccache
We describe a methodology to automatically turn arbitrary ARMv8 programs into alphanumeric executable polymorphic shellcodes.
Cryptography and Security
no code implementations • 24 Mar 2014 • Thomas Bourgeat, Julien Bringer, Herve Chabanne, Robin Champenois, Jeremie Clement, Houda Ferradi, Marc Heinrich, Paul Melotti, David Naccache, Antoine Voizard
Whilst useful in many contexts, this work is mainly motivated by fingerprint matching.