Zobrazeno 1 - 10
of 80
pro vyhledávání: '"Alberge, Florence"'
This paper introduces a universal approach to seamlessly combine out-of-distribution (OOD) detection scores. These scores encompass a wide range of techniques that leverage the self-confidence of deep learning models and the anomalous behavior of fea
Externí odkaz:
http://arxiv.org/abs/2406.16045
This paper tackles the challenge of detecting unreliable behavior in regression algorithms, which may arise from intrinsic variability (e.g., aleatoric uncertainty) or modeling errors (e.g., model uncertainty). First, we formally introduce the notion
Externí odkaz:
http://arxiv.org/abs/2406.06968
Reliable out-of-distribution (OOD) detection is fundamental to implementing safer modern machine learning (ML) systems. In this paper, we introduce Igeood, an effective method for detecting OOD samples. Igeood applies to any pre-trained neural networ
Externí odkaz:
http://arxiv.org/abs/2203.07798
On the efficiency of transmission strategies for broadcast channels using finite size constellations
In this paper, achievable rates regions are derived for power constrained Gaussian broadcast channel of two users using finite dimension constellations. Various transmission strategies are studied, namely superposition coding (SC) and superposition m
Externí odkaz:
http://arxiv.org/abs/1403.2702
Autor:
Alberge, Florence.
Th. doct.--Signal et images--Paris--ENST, 1999.
Bibliogr. p. 145-150. Résumé.
Bibliogr. p. 145-150. Résumé.
Externí odkaz:
http://catalogue.bnf.fr/ark:/12148/cb37111849h
Publikováno v:
ICASSP, Taipei : Taiwan (2009)
Iterative decoding was not originally introduced as the solution to an optimization problem rendering the analysis of its convergence very difficult. In this paper, we investigate the link between iterative decoding and classical optimization techniq
Externí odkaz:
http://arxiv.org/abs/1001.1917
Publikováno v:
ICASSP, Taipei : Taiwan (2009)
The paper first recalls the Blahut Arimoto algorithm for computing the capacity of arbitrary discrete memoryless channels, as an example of an iterative algorithm working with probability density estimates. Then, a geometrical interpretation of this
Externí odkaz:
http://arxiv.org/abs/1001.1915
Publikováno v:
GRETSI, Dijon : France (2009)
This paper recalls the proximal point method. We study two iterative algorithms: the Blahut-Arimoto algorithm for computing the capacity of arbitrary discrete memoryless channels, as an example of an iterative algorithm working with probability densi
Externí odkaz:
http://arxiv.org/abs/1001.1912
Reliable out-of-distribution (OOD) detection is fundamental to implementing safer modern machine learning (ML) systems. In this paper, we introduce Igeood, an effective method for detecting OOD samples. Igeood applies to any pre-trained neural networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::29927736ee28b976cb24692741ed9e29
Autor:
Alberge, Florence
Publikováno v:
XXVIIème Colloque francophone de traitement du signal et des images (Gretsi 2019)
XXVIIème Colloque francophone de traitement du signal et des images (Gretsi 2019), Aug 2019, Lille, France
XXVIIème Colloque francophone de traitement du signal et des images (Gretsi 2019), Aug 2019, Lille, France
International audience; Nous nous intéressons à l'utilisation partagée du spectre entre un radar et un système de communication sans fil. C'est une des pistes envisagée pour lutter contre la congestion des réseaux de communication. Le canal de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e4eb0470df3fa8ce72ce6d1593aad7aa
https://hal.archives-ouvertes.fr/hal-02172721
https://hal.archives-ouvertes.fr/hal-02172721