526 citations
- Centre National de la Recherche ScientifiqueFR83 papers
- Université Jean MonnetFR62 papers
- Lyon 1 UniversitéFR39 papers
- Institut d’Optique Graduate SchoolFR13 papers
- Leading Health CareSE13 papers
- Laboratoire Traitement et Communication de l’InformationFR12 papers
- Télécom ParisFR11 papers
- Centre de Recherche Astrophysique de LyonFR10 papers
- Université de LyonFR10 papers
- École Normale Supérieure de LyonFR9 papers
- Institut Polytechnique de ParisFR9 papers
- Université Paris-SaclayFR9 papers
156 papers
Implémentation Efficiente de Fonctions de Convolution sur FPGA à l'Aide de Blocs Paramétrables et d'Approximations Polynomiales
Philippe Magalhães, Virginie Fresse, Benoît Suffran +1
Implementing convolutional neural networks (CNNs) on field-programmable gate arrays (FPGAs) has emerged as a promising alternative to GPUs, offering lower latency, greater power ef…
A Resource-Driven Approach for Implementing CNNs on FPGAs Using Adaptive IPs
Philippe Magalhães, Virginie Fresse, Benoît Suffran +1
The increasing demand for real-time, low-latency artificial intelligence applications has propelled the use of Field-Programmable Gate Arrays (FPGAs) for Convolutional Neural Netwo…
PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures
Hind Atbir, Farah Cherfaoui, Guillaume Metzler +2
PAC generalization bounds on the risk, when expressed in terms of the expected loss, are often insufficient to capture imbalances between subgroups in the data. To overcome this li…
Photonic Learning in Ultrafast Laser-Induced Complexity
Fayad Ali Banna, Eduardo Brandao, Anthony Nakhoul +3
How can one design complex systems capable of learning for a given functionality? In the context of ultrafast laser-surface interaction, we unravel the nature of learning schemes t…
Méthode de quadrature pour les PINNs fondée théoriquement sur la hessienne des résiduels
Antoine Caradot, Rémi Emonet, Amaury Habrard +2
Physics-informed Neural Networks (PINNs) have emerged as an efficient way to learn surrogate neural solvers of PDEs by embedding the physical model in the loss function and minimiz…
Acoustic evaluation of a neural network dedicated to the detection of animal vocalisations
Jérémy Rouch, M Ducrettet, S Haupert +2
The accessibility of long-duration recorders, adapted to sometimes demanding field conditions, has enabled the deployment of extensive animal population monitoring campaigns throug…