Zobrazeno 1 - 10
of 11 041
pro vyhledávání: '"Lemaire P."'
Various numerical methods used for solving partial differential equations (PDE) result in tridiagonal systems. Solving tridiagonal systems on distributed-memory environments is not straightforward, and often requires significant amount of communicati
Externí odkaz:
http://arxiv.org/abs/2411.13532
We introduce a new class of neural networks designed to be convex functions of their inputs, leveraging the principle that any convex function can be represented as the supremum of the affine functions it dominates. These neural networks, inherently
Externí odkaz:
http://arxiv.org/abs/2411.12854
Publikováno v:
Transactions on Machine Learning Research 2024
Mislabeled examples are ubiquitous in real-world machine learning datasets, advocating the development of techniques for automatic detection. We show that most mislabeled detection methods can be viewed as probing trained machine learning models usin
Externí odkaz:
http://arxiv.org/abs/2410.15772
Autor:
Hoarau, Arthur, Lemaire, Vincent
Recent research in machine learning has given rise to a flourishing literature on the quantification and decomposition of model uncertainty. This information can be very useful during interactions with the learner, such as in active learning or adapt
Externí odkaz:
http://arxiv.org/abs/2409.08105
Autor:
Renault, Aurélien, Achenchabe, Youssef, Bertrand, Édouard, Bondu, Alexis, Cornuéjols, Antoine, Lemaire, Vincent, Dachraoui, Asma
\texttt{ml\_edm} is a Python 3 library, designed for early decision making of any learning tasks involving temporal/sequential data. The package is also modular, providing researchers an easy way to implement their own triggering strategy for classif
Externí odkaz:
http://arxiv.org/abs/2408.12925
In many situations, the measurements of a studied phenomenon are provided sequentially, and the prediction of its class needs to be made as early as possible so as not to incur too high a time penalty, but not too early and risk paying the cost of mi
Externí odkaz:
http://arxiv.org/abs/2406.18332
Autor:
Courtois, Jonathan, Novac, Pierre-Emmanuel, Lemaire, Edgar, Pegatoquet, Alain, Miramond, Benoit
The complexity of event-based object detection (OD) poses considerable challenges. Spiking Neural Networks (SNNs) show promising results and pave the way for efficient event-based OD. Despite this success, the path to efficient SNNs on embedded devic
Externí odkaz:
http://arxiv.org/abs/2406.17617
Autor:
Ahnood, Arman, Cheriton, Ross, Bruneau, Anne, Belcourt, James A., Ndabakuranye, Jean Pierre, Lemaire, William, Hilkes, Rob, Fontaine, Réjean, Cook, John P. D., Hinzer, Karin, Prawer, Steven
Publikováno v:
Advanced Biosystems 4.11 (2020): 2000055
The design and benchtop operation of a wireless miniature epiretinal stimulator implant is reported. The implant is optically powered and controlled using safe illumination at near-infrared wavelengths. An application-specific integrated circuit (ASI
Externí odkaz:
http://arxiv.org/abs/2407.04720
Autor:
Boitier, William, Del Pozzo, Antonella, García-Pérez, Álvaro, Gazut, Stephane, Jobic, Pierre, Lemaire, Alexis, Mahe, Erwan, Mayoue, Aurelien, Perion, Maxence, Rezende, Tuanir Franca, Singh, Deepika, Tucci-Piergiovanni, Sara
Federated Learning is a decentralized framework that enables multiple clients to collaboratively train a machine learning model under the orchestration of a central server without sharing their local data. The centrality of this framework represents
Externí odkaz:
http://arxiv.org/abs/2406.03608
Autor:
Lemaire, Pierre, Furno, Angelo, Rubrichi, Stefania, Bondu, Alexis, Smoreda, Zbigniew, Ziemlicki, Cezary, Faouzi, Nour-Eddin El, Gaume, Eric
Network Signalling Data (NSD) have the potential to provide continuous spatio-temporal information about the presence, mobility, and usage patterns of cell phone services by individuals. Such information is invaluable for monitoring large urban areas
Externí odkaz:
http://arxiv.org/abs/2405.19125