Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Léonardon, Mathieu"'
Autor:
Ribeiro, Lucas Grativol, Leonardon, Mathieu, Muller, Guillaume, Fresse, Virginie, Arzel, Matthieu
Publikováno v:
32nd European Signal Processing Conference EUSIPCO, Aug 2024, Lyon, France
Low-Rank Adaptation (LoRA) methods have gained popularity in efficient parameter fine-tuning of models containing hundreds of billions of parameters. In this work, instead, we demonstrate the application of LoRA methods to train small-vision models i
Externí odkaz:
http://arxiv.org/abs/2406.14082
Autor:
Ribeiro, Lucas Grativol, Gauthier, Lubin, Leonardon, Mathieu, Morlier, Jérémy, Lavrard-Meyer, Antoine, Muller, Guillaume, Fresse, Virginie, Arzel, Matthieu
Publikováno v:
ISCAS 2024 : IEEE International Symposium on Circuits and Systems, May 2024, Singapore, Singapore
This paper tackles the challenges of implementing few-shot learning on embedded systems, specifically FPGA SoCs, a vital approach for adapting to diverse classification tasks, especially when the costs of data acquisition or labeling prove to be proh
Externí odkaz:
http://arxiv.org/abs/2404.19354
Autor:
Ribeiro, Lucas Grativol, Leonardon, Mathieu, Muller, Guillaume, Fresse, Virginie, Arzel, Matthieu
Publikováno v:
IEEE 30th International Conference on Electronics, Circuits and Systems, Dec 2023, Istanbul, Turkey
Federated Learning (FL) is a promising distributed method for edge-level machine learning, particularly for privacysensitive applications such as those in military and medical domains, where client data cannot be shared or transferred to a cloud comp
Externí odkaz:
http://arxiv.org/abs/2310.14693
Autor:
Ganji, Darshan C., Ashfaq, Saad, Saboori, Ehsan, Sah, Sudhakar, Mitra, Saptarshi, AskariHemmat, MohammadHossein, Hoffman, Alexander, Hassanien, Ahmed, Léonardon, Mathieu
A lot of recent progress has been made in ultra low-bit quantization, promising significant improvements in latency, memory footprint and energy consumption on edge devices. Quantization methods such as Learned Step Size Quantization can achieve mode
Externí odkaz:
http://arxiv.org/abs/2304.09049
Autor:
Tessier, Hugo, Gripon, Vincent, Léonardon, Mathieu, Arzel, Matthieu, Bertrand, David, Hannagan, Thomas
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 limitations in terms of energy consumption prohibit the use of very large netwo
Externí odkaz:
http://arxiv.org/abs/2206.06255
Autor:
Tessier, Hugo, Gripon, Vincent, Léonardon, Mathieu, Arzel, Matthieu, Bertrand, David, Hannagan, Thomas
Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many computer vision tasks. However, depending on the architecture, pruning introduces dimensional discrepancies which preven
Externí odkaz:
http://arxiv.org/abs/2206.06247
Autor:
Léonardon, Mathieu, Gripon, Vincent
Polar codes can theoretically achieve very competitive Frame Error Rates. In practice, their performance may depend on the chosen decoding procedure, as well as other parameters of the communication system they are deployed upon. As a consequence, de
Externí odkaz:
http://arxiv.org/abs/2105.04922
Autor:
Léonardon, Mathieu
Les codes polaires constituent une classe de codes correcteurs d’erreurs inventés récemment qui suscite l’intérêt des chercheurs et des industriels, comme en atteste leur sélection pour le codage des canaux de contrôle dans la prochaine gé
Externí odkaz:
http://www.theses.fr/2018BORD0399/document
Autor:
Tessier, Hugo, Gripon, Vincent, Léonardon, Mathieu, Arzel, Matthieu, Hannagan, Thomas, Bertrand, David
Publikováno v:
Journal of Imaging 8 (2022), no. 3: 64
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 approaches still face core issues that hinder their performance or sca
Externí odkaz:
http://arxiv.org/abs/2011.10520
Autor:
Léonardon, Mathieu, Cassagne, Adrien, Leroux, Camille, Jégo, Christophe, Hamelin, Louis-Philippe, Savaria, Yvon
Flexibility is one mandatory aspect of channel coding in modern wireless communication systems. Among other things, the channel decoder has to support several code lengths and code rates. This need for flexibility applies to polar codes that are cons
Externí odkaz:
http://arxiv.org/abs/1710.08314