Zobrazeno 1 - 10
of 168
pro vyhledávání: '"Salmon, Joseph"'
Autor:
Lefort, Tanguy, Affouard, Antoine, Charlier, Benjamin, Lombardo, Jean-Christophe, Chouet, Mathias, Goëau, Hervé, Salmon, Joseph, Bonnet, Pierre, Joly, Alexis
Deep learning models for plant species identification rely on large annotated datasets. The PlantNet system enables global data collection by allowing users to upload and annotate plant observations, leading to noisy labels due to diverse user skills
Externí odkaz:
http://arxiv.org/abs/2406.03356
Average-K classification is an alternative to top-K classification in which the number of labels returned varies with the ambiguity of the input image but must average to K over all the samples. A simple method to solve this task is to threshold the
Externí odkaz:
http://arxiv.org/abs/2303.18118
In supervised learning - for instance in image classification - modern massive datasets are commonly labeled by a crowd of workers. The obtained labels in this crowdsourcing setting are then aggregated for training, generally leveraging a per-worker
Externí odkaz:
http://arxiv.org/abs/2209.15380
In this paper, we study differentially private empirical risk minimization (DP-ERM). It has been shown that the worst-case utility of DP-ERM reduces polynomially as the dimension increases. This is a major obstacle to privately learning large machine
Externí odkaz:
http://arxiv.org/abs/2207.01560
Autor:
Moreau, Thomas, Massias, Mathurin, Gramfort, Alexandre, Ablin, Pierre, Bannier, Pierre-Antoine, Charlier, Benjamin, Dagréou, Mathieu, la Tour, Tom Dupré, Durif, Ghislain, Dantas, Cassio F., Klopfenstein, Quentin, Larsson, Johan, Lai, En, Lefort, Tanguy, Malézieux, Benoit, Moufad, Badr, Nguyen, Binh T., Rakotomamonjy, Alain, Ramzi, Zaccharie, Salmon, Joseph, Vaiter, Samuel
Numerical validation is at the core of machine learning research as it allows to assess the actual impact of new methods, and to confirm the agreement between theory and practice. Yet, the rapid development of the field poses several challenges: rese
Externí odkaz:
http://arxiv.org/abs/2206.13424
Autor:
Salmon, Joseph L.
The goal of this research project was to determine the content of the discourse occurring in grade-level meetings and coaching sessions and participants' perceptions of how the conversations in these two venues impacted learning and practice for indi
Externí odkaz:
http://hdl.handle.net/10919/77112
http://scholar.lib.vt.edu/theses/available/etd-06182012-085313/
http://scholar.lib.vt.edu/theses/available/etd-06182012-085313/
Publikováno v:
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:7208-7222, 2022
In modern classification tasks, the number of labels is getting larger and larger, as is the size of the datasets encountered in practice. As the number of classes increases, class ambiguity and class imbalance become more and more problematic to ach
Externí odkaz:
http://arxiv.org/abs/2202.02193
Sparsity priors are commonly used in denoising and image reconstruction. For analysis-type priors, a dictionary defines a representation of signals that is likely to be sparse. In most situations, this dictionary is not known, and is to be recovered
Externí odkaz:
http://arxiv.org/abs/2112.07990
While Weighted Lasso sparse regression has appealing statistical guarantees that would entail a major real-world impact in finance, genomics, and brain imaging applications, it is typically scarcely adopted due to its complex high-dimensional space c
Externí odkaz:
http://arxiv.org/abs/2111.02790
Estimators based on non-convex sparsity-promoting penalties were shown to yield state-of-the-art solutions to the magneto-/electroencephalography (M/EEG) brain source localization problem. In this paper we tackle the model selection problem of these
Externí odkaz:
http://arxiv.org/abs/2112.12178