Zobrazeno 1 - 10
of 7 386
pro vyhledávání: '"Najman, A"'
Autor:
Derickx, Maarten, Najman, Filip
Let $E$ be an elliptic curve over a quartic field $K$. By the Mordell-Weil theorem, $E(K)$ is a finitely generated group. We determine all the possibilities for the torsion group $E(K)_{tor}$ where $K$ ranges over all quartic fields $K$ and $E$ range
Externí odkaz:
http://arxiv.org/abs/2412.16016
Publikováno v:
2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Dec 2024, Lisbon (Portugal), Portugal
Annotating 3D medical images demands expert knowledge and is time-consuming. As a result, semi-supervised learning (SSL) approaches have gained significant interest in 3D medical image segmentation. The significant size differences among various orga
Externí odkaz:
http://arxiv.org/abs/2410.14210
Autor:
Videau, Mathurin, Zameshina, Mariia, Leite, Alessandro, Najman, Laurent, Schoenauer, Marc, Teytaud, Olivier
AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying non-differentiable optimization, including evolutionary methods, to refine fully-trained machine learning models by optimizing a set of carefully chosen parameters or hyperp
Externí odkaz:
http://arxiv.org/abs/2410.11330
Autor:
Labiad, Ismail, Bäck, Thomas, Fernandez, Pierre, Najman, Laurent, Sander, Tom, Ye, Furong, Zameshina, Mariia, Teytaud, Olivier
In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an excellent ad hoc distribution of initial attacks. However, these attac
Externí odkaz:
http://arxiv.org/abs/2409.15119
Challenges persist in providing interpretable explanations for neural network reasoning in explainable AI (xAI). Existing methods like Integrated Gradients produce noisy maps, and LIME, while intuitive, may deviate from the model's reasoning. We intr
Externí odkaz:
http://arxiv.org/abs/2406.13257
A classifier is, in its essence, a function which takes an input and returns the class of the input and implicitly assumes an underlying distribution. We argue in this article that one has to move away from this basic tenet to obtain generalisation a
Externí odkaz:
http://arxiv.org/abs/2405.11573
Autor:
Bosansky, Branislav, Hospodkova, Lada, Najman, Michal, Rigaki, Maria, Babayeva, Elnaz, Lisy, Viliam
The accuracy of deployed malware-detection classifiers degrades over time due to changes in data distributions and increasing discrepancies between training and testing data. This phenomenon is known as the concept drift. While the concept drift can
Externí odkaz:
http://arxiv.org/abs/2404.09352
Autor:
Garrido, Quentin, Assran, Mahmoud, Ballas, Nicolas, Bardes, Adrien, Najman, Laurent, LeCun, Yann
Joint-Embedding Predictive Architecture (JEPA) has emerged as a promising self-supervised approach that learns by leveraging a world model. While previously limited to predicting missing parts of an input, we explore how to generalize the JEPA predic
Externí odkaz:
http://arxiv.org/abs/2403.00504
In this paper, we propose a class of non-parametric classifiers, that learn arbitrary boundaries and generalize well. Our approach is based on a novel way to regularize 1NN classifiers using a greedy approach. We refer to this class of classifiers as
Externí odkaz:
http://arxiv.org/abs/2402.08405
A persistent challenge in the field of Intelligent Transportation Systems is to extract accurate traffic insights from geographic regions with scarce or no data coverage. To this end, we propose solutions for speed prediction using sparse GPS data po
Externí odkaz:
http://arxiv.org/abs/2402.07507