Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Bontonou, Myriam"'
Autor:
Xompero, Alessio, Bontonou, Myriam, Arbona, Jean-Michel, Benetos, Emmanouil, Cavallaro, Andrea
Accurately predicting whether an image is private before sharing it online is difficult due to the vast variety of content and the subjective nature of privacy itself. In this paper, we evaluate privacy models that use objects extracted from an image
Externí odkaz:
http://arxiv.org/abs/2405.01646
Autor:
Bontonou, Myriam, Haget, Anaïs, Boulougouri, Maria, Audit, Benjamin, Borgnat, Pierre, Arbona, Jean-Michel
Many machine learning models have been proposed to classify phenotypes from gene expression data. In addition to their good performance, these models can potentially provide some understanding of phenotypes by extracting explanations for their decisi
Externí odkaz:
http://arxiv.org/abs/2402.00926
Autor:
Bontonou, Myriam, Haget, Anaïs, Boulougouri, Maria, Arbona, Jean-Michel, Audit, Benjamin, Borgnat, Pierre
Understanding the molecular processes that drive cellular life is a fundamental question in biological research. Ambitious programs have gathered a number of molecular datasets on large populations. To decipher the complex cellular interactions, rece
Externí odkaz:
http://arxiv.org/abs/2303.11336
Autor:
Lassance, Carlos, Bontonou, Myriam, Hamidouche, Mounia, Pasdeloup, Bastien, Drumetz, Lucas, Gripon, Vincent
In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations. For example, DNNs require a lot of t
Externí odkaz:
http://arxiv.org/abs/2110.03999
It is very common to face classification problems where the number of available labeled samples is small compared to their dimension. These conditions are likely to cause underdetermined settings, with high risk of overfitting. To improve the general
Externí odkaz:
http://arxiv.org/abs/2108.10427
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) to represent the latent spaces of trained DNN architect
Externí odkaz:
http://arxiv.org/abs/2011.12737
Few-shot learning addresses problems for which a limited number of training examples are available. So far, the field has been mostly driven by applications in computer vision. Here, we are interested in adapting recently introduced few-shot methods
Externí odkaz:
http://arxiv.org/abs/2010.12500
In the context of few-shot learning, one cannot measure the generalization ability of a trained classifier using validation sets, due to the small number of labeled samples. In this paper, we are interested in finding alternatives to answer the quest
Externí odkaz:
http://arxiv.org/abs/2007.04238
Autor:
Lassance, Carlos, Bontonou, Myriam, Hacene, Ghouthi Boukli, Gripon, Vincent, Tang, Jian, Ortega, Antonio
In most cases deep learning architectures are trained disregarding the amount of operations and energy consumption. However, some applications, like embedded systems, can be resource-constrained during inference. A popular approach to reduce the size
Externí odkaz:
http://arxiv.org/abs/1911.03080
Publikováno v:
Wavelets and Sparsity XVIII, Aug 2019, San Diego, United States
Predicting the future of Graph-supported Time Series (GTS) is a key challenge in many domains, such as climate monitoring, finance or neuroimaging. Yet it is a highly difficult problem as it requires to account jointly for time and graph (spatial) de
Externí odkaz:
http://arxiv.org/abs/1908.06868