Výsledky vyhledávání

Report

FLoCoRA: Federated learning compression with low-rank adaptation

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

Zobrazit plný text záznamu

Report

PEFSL: A deployment Pipeline for Embedded Few-Shot Learning on a FPGA SoC

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

Zobrazit plný text záznamu

Report

Federated learning compression designed for lightweight communications

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

Zobrazit plný text záznamu

Akademický článek

UP Bio-Circular Solutions: A Sustainable Approach to Consumer Goods Formulation.

Autor: Arzel, M.¹, Chabert, M.²

Publikováno v: SOFW Journal (English version). Oct2024, Vol. 150 Issue 10, p44-47. 4p.

Zobrazit plný text záznamu

Report

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

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

Zobrazit plný text záznamu

Report

Leveraging Structured Pruning of Convolutional Neural Networks

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

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání