133 citations
- Laboratoire Interdisciplinaire des Sciences du NumériqueFR15 papers
- Laboratoire d’Informatique et SystèmesFR7 papers
- Anstalt für Verbrennungskraftmaschinen List (Austria)AT6 papers
- Université Paris-SaclayFR5 papers
- Aix-Marseille UniversitéFR4 papers
- École Nationale Supérieure d’Informatique pour l’Industrie et l’EntrepriseFR4 papers
- Centre BorelliFR3 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et EnergétiqueFR3 papers
- Shanghai Jiao Tong UniversityCN3 papers
- Université de Bretagne OccidentaleFR3 papers
- Université Toulouse III - Paul SabatierFR3 papers
7 papers · 1 filter
The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound
Clément Morand, Anne-Laure Ligozat, Aurélie Névéol
Recent Machine Learning (ML) approaches have shown increased performance on benchmarks at the cost of escalating compute demands. Hardware, algorithmic and carbon optimizations hav…
Growth strategies for arbitrary DAG neural architectures
Stella Douka, Manon Verbockhaven, Théo Rudkiewicz +4
Deep learning has shown impressive results obtained at the cost of training huge neural networks. However, the larger the architecture, the higher the computational, financial, and…
How Green Can AI Be? A Study of Trends in Machine Learning Environmental Impacts
Clément Morand, Anne-Laure Ligozat, Aurélie Névéol
The compute requirements associated with training Artificial Intelligence (AI) models have increased exponentially over time. Optimisation strategies aim to reduce the energy consu…
Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
Zhen Xu, Lanning Wei, Huan Zhao +4
Graph structured data is ubiquitous in daily life and scientific areas and has attracted increasing attention. Graph Neural Networks (GNNs) have been proved to be effective in mode…
Physics-aware deep neural networks for surrogate modeling of turbulent natural convection
Didier Lucor, Atul Agrawal, Anne Sergent
Recent works have explored the potential of machine learning as data-driven turbulence closures for RANS and LES techniques. Beyond these advances, the high expressivity and agilit…
Deep Networks with Adaptive Nyström Approximation
Luc Giffon, Stéphane Ayache, Thierry Artières +1
Recent work has focused on combining kernel methods and deep learning to exploit the best of the two approaches. Here, we introduce a new architecture of neural networks in which w…