Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Ducoffe, Mélanie"'
Autor:
Cappi, Cyril, Cohen, Noémie, Ducoffe, Mélanie, Gabreau, Christophe, Gardes, Laurent, Gauffriau, Adrien, Ginestet, Jean-Brice, Mamalet, Franck, Mussot, Vincent, Pagetti, Claire, Vigouroux, David
This paper focuses on a Vision-based Landing task and presents the design and the validation of a dataset that would comply with the Operational Design Domain (ODD) of a Machine-Learning (ML) system. Relying on emerging certification standards, we de
Externí odkaz:
http://arxiv.org/abs/2406.14027
Autor:
Cohen, Noémie, Ducoffe, Mélanie, Boumazouza, Ryma, Gabreau, Christophe, Pagetti, Claire, Pucel, Xavier, Galametz, Audrey
We introduce a novel Interval Bound Propagation (IBP) approach for the formal verification of object detection models, specifically targeting the Intersection over Union (IoU) metric. The approach has been implemented in an open source code, named IB
Externí odkaz:
http://arxiv.org/abs/2403.08788
Autor:
Ducoffe, Mélanie, Povéda, Guillaume, Galametz, Audrey, Boumazouza, Ryma, Martin, Marion-Cécile, Baris, Julien, Daverschot, Derk, O'Higgins, Eugene
Surrogate Neural Networks are nowadays routinely used in industry as substitutes for computationally demanding engineering simulations (e.g., in structural analysis). They allow to generate faster predictions and thus analyses in industrial applicati
Externí odkaz:
http://arxiv.org/abs/2401.06821
Autor:
Elboher, Yizhak, Elsaleh, Raya, Isac, Omri, Ducoffe, Mélanie, Galametz, Audrey, Povéda, Guillaume, Boumazouza, Ryma, Cohen, Noémie, Katz, Guy
As deep neural networks (DNNs) are becoming the prominent solution for many computational problems, the aviation industry seeks to explore their potential in alleviating pilot workload and in improving operational safety. However, the use of DNNs in
Externí odkaz:
http://arxiv.org/abs/2402.00035
Autor:
Ducoffe, Mélanie, Carrere, Maxime, Féliers, Léo, Gauffriau, Adrien, Mussot, Vincent, Pagetti, Claire, Sammour, Thierry
As the interest in autonomous systems continues to grow, one of the major challenges is collecting sufficient and representative real-world data. Despite the strong practical and commercial interest in autonomous landing systems in the aerospace fiel
Externí odkaz:
http://arxiv.org/abs/2304.09938
Autor:
Fel, Thomas, Ducoffe, Melanie, Vigouroux, David, Cadene, Remi, Capelle, Mikael, Nicodeme, Claire, Serre, Thomas
Publikováno v:
Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023
A variety of methods have been proposed to try to explain how deep neural networks make their decisions. Key to those approaches is the need to sample the pixel space efficiently in order to derive importance maps. However, it has been shown that the
Externí odkaz:
http://arxiv.org/abs/2202.07728
Publikováno v:
AAAI-21, workshop on safeAI, Feb 2021, Valence (Virtual), Spain
We describe a complete method that learns a neural network which is guaranteed to overestimate a reference function on a given domain. The neural network can then be used as a surrogate for the reference function. The method involves two steps. In th
Externí odkaz:
http://arxiv.org/abs/2101.11717
Autor:
Ducoffe, Mélanie
Notre travail est présenté en trois parties indépendantes. Tout d'abord, nous proposons trois heuristiques d'apprentissage actif pour les réseaux de neurones profonds : Nous mettons à l'échelle le `query by committee', qui agrège la décision
Externí odkaz:
http://www.theses.fr/2018AZUR4115/document
The ability to detect anomalies in time series is considered highly valuable in numerous application domains. The sequential nature of time series objects is responsible for an additional feature complexity, ultimately requiring specialized approache
Externí odkaz:
http://arxiv.org/abs/2005.07031
Deep learning applications have been thriving over the last decade in many different domains, including computer vision and natural language understanding. The drivers for the vibrant development of deep learning have been the availability of abundan
Externí odkaz:
http://arxiv.org/abs/2005.02144