Zobrazeno 1 - 10
of 1 638
pro vyhledávání: '"Frenay, P"'
Numerous studies have recently focused on incorporating different variations of equivariance in Convolutional Neural Networks (CNNs). In particular, rotation-equivariance has gathered significant attention due to its relevance in many applications re
Externí odkaz:
http://arxiv.org/abs/2412.09182
Autor:
Beatrice Seligardi
Publikováno v:
Between, Vol 11, Iss 22 (2021)
Recensione di Beniamino Della Gala, Adrien Frenay, Filippo Milani, Lucia Quaquarelli (eds.), Lasciate socchiuse le porte. Mobilità, attraversamenti, sconfinamenti
Externí odkaz:
https://doaj.org/article/155e93303b2a4aed81ad310de2d6d0ef
Autor:
Stassin, Sédrick, Englebert, Alexandre, Nanfack, Géraldin, Albert, Julien, Versbraegen, Nassim, Peiffer, Gilles, Doh, Miriam, Riche, Nicolas, Frenay, Benoît, De Vleeschouwer, Christophe
EXplainable Artificial Intelligence (XAI) aims to help users to grasp the reasoning behind the predictions of an Artificial Intelligence (AI) system. Many XAI approaches have emerged in recent years. Consequently, a subfield related to the evaluation
Externí odkaz:
http://arxiv.org/abs/2305.16361
For many years, it has been shown how much exploiting equivariances can be beneficial when solving image analysis tasks. For example, the superiority of convolutional neural networks (CNNs) compared to dense networks mainly comes from an elegant expl
Externí odkaz:
http://arxiv.org/abs/2304.09214
In this study, a new Anomaly Detection (AD) approach for industrial and medical images is proposed. This method leverages the theoretical strengths of unsupervised learning and the data availability of both normal and abnormal classes. Indeed, the AD
Externí odkaz:
http://arxiv.org/abs/2302.05154
Publikováno v:
Mach Learn (2023)
In recent years, the industrial sector has evolved towards its fourth revolution. The quality control domain is particularly interested in advanced machine learning for computer vision anomaly detection. Nevertheless, several challenges have to be fa
Externí odkaz:
http://arxiv.org/abs/2211.15513
Autor:
Hélène Bartak, Tasnim Fareh, Nouha Ben Othman, Delphine Viard, Mikael Cohen, Fanny Rocher, Elliot Ewig, Milou-Daniel Drici, Christine Lebrun-Frenay
Publikováno v:
Neurology and Therapy, Vol 13, Iss 3, Pp 917-930 (2024)
Abstract Introduction Over the past few years, anti-CD20 therapies like rituximab, ocrelizumab or ofatumumab have seen an increase in interest in the treatment of neurological autoimmune disorders such as multiple sclerosis (MS), neuromyelitis optica
Externí odkaz:
https://doaj.org/article/68c221405b3a4e8c8d9ce0e267db9995
Autor:
Cassandre Landes‐Chateau, Michael Levraut, Darin T. Okuda, Albert Themelin, Mikael Cohen, Orhun H. Kantarci, Aksel Siva, Daniel Pelletier, Lydiane Mondot, Christine Lebrun‐Frenay, on behalf RISConsortium
Publikováno v:
Annals of Clinical and Translational Neurology, Vol 11, Iss 3, Pp 662-672 (2024)
Abstract Objective The radiologically isolated syndrome (RIS) represents the earliest detectable preclinical phase of multiple sclerosis (MS). Increasing evidence suggests that the central vein sign (CVS) enhances lesion specificity, allowing for gre
Externí odkaz:
https://doaj.org/article/9abdd644db594616ba70706ce0752b3c
Autor:
Danièle Périsset
Publikováno v:
Schweizerische Zeitschrift für Bildungswissenschaften, Vol 30, Iss 3 (2008)
Recension
Externí odkaz:
https://doaj.org/article/06cb573f8f8648b39a78ac6ca655a6f3
A plethora of dimensionality reduction techniques have emerged over the past decades, leaving researchers and analysts with a wide variety of choices for reducing their data, all the more so given some techniques come with additional parametrization
Externí odkaz:
http://arxiv.org/abs/2105.09275