Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Bernhard, Rémi"'
Autor:
Bernhard, Rémi1 (AUTHOR) rbernhard@quantificare.com, Bletterer, Arnaud1 (AUTHOR), Le Caro, Maëlle1 (AUTHOR), García Álvarez, Estrella2 (AUTHOR), Kostov, Belchin2 (AUTHOR), Herrera Egea, Diego2 (AUTHOR)
Publikováno v:
Dermatology & Therapy. Nov2024, Vol. 14 Issue 11, p2953-2969. 17p.
For many IoT domains, Machine Learning and more particularly Deep Learning brings very efficient solutions to handle complex data and perform challenging and mostly critical tasks. However, the deployment of models in a large variety of devices faces
Externí odkaz:
http://arxiv.org/abs/2105.01403
Utilization of Machine Learning (ML) algorithms, especially Deep Neural Network (DNN) models, becomes a widely accepted standard in many domains more particularly IoT-based systems. DNN models reach impressive performances in several sensitive fields
Externí odkaz:
http://arxiv.org/abs/2105.01401
Autor:
Bernhard, Rémi, Moellic, Pierre-Alain, Mermillod, Martial, Bourrier, Yannick, Cohendet, Romain, Solinas, Miguel, Reyboz, Marina
Adversarial examples mainly exploit changes to input pixels to which humans are not sensitive to, and arise from the fact that models make decisions based on uninterpretable features. Interestingly, cognitive science reports that the process of inter
Externí odkaz:
http://arxiv.org/abs/2104.12679
The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this paper, we pa
Externí odkaz:
http://arxiv.org/abs/2004.04919
As the will to deploy neural networks models on embedded systems grows, and considering the related memory footprint and energy consumption issues, finding lighter solutions to store neural networks such as weight quantization and more efficient infe
Externí odkaz:
http://arxiv.org/abs/1909.12741
Autor:
de Vieilleville, François, May, Stéphane, Lagrange, Adrien, Dupuis, A, Ruiloba, Rosa, Ngolè Mboula, Fred, Bitard-Feildel, Tristan, Nogues, Erwan, Larroche, Corentin, Mazel, Johan, Clémençon, Stephan, Burgot, Romain, Gaurier, Alric, Hulot, Louis, Isaac-Dognin, Léo, Leichtnam, Laetitia, Totel, Eric, Prigent, Nicolas, Mé, Ludovic, Bernhard, Rémi, Moëllic, Pierre-Alain, Dutertre, Jean-Max, Kapusta, Katarzyna, Thouvenot, Vincent, Bettan, Olivier, Charrier, Tristan, Bonnafoux, Luc, Puig, Francisco-Pierre, Lhoest, Quentin, Renault, Thomas, Benamira, Adrien, Bonnet, Benoit, Furon, Teddy, Bas, Patrick, Farcy, Benjamin, Gil-Casals, Silvia, Mattioli, Juliette, Fiammante, Marc, Lambert, Marc, Bresson, Roman, Cohen, Johanne, Hullermeier, Eyke, Labreuche, Christophe, Sebag, Michele, Thebaud, Thomas, Larcher, Anthony, Le Lan, Gaël, Nour, Nouredine, Belhaj-Soullami, Reda, Buron, Cédric, Peres, Alain, Barbaresco, Frédéric, D’acremont, Antoine, Quin, Guillaume, Baussard, Alexandre, Fablet, Ronan, Corbineau, Marie-Caroline, Morge-Rollet, Louis, Le Roy, Frederic, Le Jeune, Denis, Gautier, Roland, Camus, Benjamin, Monteux, Eric, Vermet, Mikaël, Goupilleau, Alex, Ceillier, Tugdual
Publikováno v:
CAID 2020-Second Conference on Artificial Intelligence for Defence
CAID 2020-Second Conference on Artificial Intelligence for Defence, Dec 2020, Rennes, France. 2021
CAID 2020-Second Conference on Artificial Intelligence for Defence, Dec 2020, Rennes, France. 2021
National audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f4976e6dd0bf6e39aa003f13538847cf
https://hal.archives-ouvertes.fr/hal-03206297/document
https://hal.archives-ouvertes.fr/hal-03206297/document
Autor:
Cohendet, Romain, Solinas, Miguel, Bernhard, Rémi, Reyboz, Marina, Moellic, Pierre-Alain, Bourrier, Yannick, Mermillod, Martial
Publikováno v:
ICMLA 2021-20th IEEE International Cconference on Machine Learning and Applications
ICMLA 2021-20th IEEE International Cconference on Machine Learning and Applications, Dec 2021, Pasadena (Virtual event), United States
ICMLA 2021-20th IEEE International Cconference on Machine Learning and Applications, Dec 2021, Pasadena (Virtual event), United States
International audience; The vulnerability of Deep Neural Network (DNN) modelsto maliciously crafted adversarial perturbations is acritical topic considering their ongoing large-scale deployment.In this work, we explore an interesting phenomenonthat o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75de3727553bcffd56f8b1829417c7f6
https://hal.archives-ouvertes.fr/hal-03173407
https://hal.archives-ouvertes.fr/hal-03173407
Autor:
Bernhard, Rémi
Regarding the success of deep learning in various tasks, ranging from image classification to speech recognition, there is a growing will to deploy neural networks models in the everyday life. However, these models have been shown to be vulnerable to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______166::c00fee02ee0c29871129751cf06c78a1
https://theses.hal.science/tel-03880905
https://theses.hal.science/tel-03880905
Autor:
Espagnol, G., Rames, M.H., Rashidi, Salim, Boisseau, C., Capelle, M., Bernhard, Rémi, Renaud, Raoul, Fleurat-Lessard, Francis, Lansac, Micheline, Pierronnet, Andre, Lafargue, Bernard, Kleiber, Aude
Publikováno v:
BIP, 237 p., 2004
National audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::fdf54a9daac4ce7e5352e52f01bb87ca
https://hal.inrae.fr/hal-02833724
https://hal.inrae.fr/hal-02833724