output
20162024
most citedRethinking Weight Decay For Efficient Neural Network Pruning

28 citations

7 papers

cs.MA2024

Enhancing Automotive User Experience with Dynamic Service Orchestration for Software Defined Vehicles

Pierre Laclau, Stéphane Bonnet, Bertrand Ducourthial +2

With the increasing demand for dynamic behaviors in automotive use cases, Software Defined Vehicles (SDVs) have emerged as a promising solution by bringing dynamic onboard service…

cs.NI2023★ 4 cited

Predictive Network Configuration with Hierarchical Spectral Clustering for Software Defined Vehicles

Pierre Laclau, Stéphane Bonnet, Bertrand Ducourthial +2

The increasing connectivity and autonomy of vehicles has led to a growing need for dynamic and real-time adjustments to software and network configurations. Software Defined Vehicl…

cs.NE2022★ 1 cited

Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU

Hugo Tessier, Vincent Gripon, Mathieu Léonardon +3

Deep neural networks are the state of the art in many computer vision tasks. Their deployment in the context of autonomous vehicles is of particular interest, since their limitatio…

cs.NE2020★ 28 cited

Rethinking Weight Decay For Efficient Neural Network Pruning

Hugo Tessier, Vincent Gripon, Mathieu Léonardon +3

Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks. Despite many innovations in recent decades, pruning…

physics.plasm-ph2019★ 14 cited

DIMOHA: A Time-Domain Algorithm for Traveling-Wave Tube Simulations

Damien Minenna, Yves Elskens, Frédéric André +3

To simulate traveling-wave tubes (TWTs) in time domain and more generally the wave-particle interaction in vacuum devices, we developed the DIscrete MOdel with HAmiltonian approach…

astro-ph.IM2017★ 1 cited

Making 3D movies of Northern Lights

Eric Hivon, Jean Mouette, Thierry Legault

We describe the steps necessary to create three-dimensional (3D) movies of Northern Lights or Aurorae Borealis out of real-time images taken with two distant high-resolution fish-e…