Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Jean-Michel Begon"'
Autor:
Jean-Michel Begon, Pierre Geurts
Publikováno v:
CVPR Workshops
Being able to detect irrelevant test examples with respect to deployed deep learning models is paramount to properly and safely using them. In this paper, we address the problem of rejecting such out-of-distribution (OOD) samples in a fully sample-fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c65fd3665bc12312c5fb9c582de6708f
https://doi.org/10.1109/cvprw53098.2021.00367
https://doi.org/10.1109/cvprw53098.2021.00367
Publikováno v:
Discovery Science ISBN: 9783030615260
DS
DS
We investigate several global variable importance measures derived from artificial neural networks (ANN) to address the challenging problem of feature ranking in high-dimensional unstructured problems. While several ANN (local) importance measures ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cddff012e55227cba2bc99aa4d1c9dc0
https://doi.org/10.1007/978-3-030-61527-7_16
https://doi.org/10.1007/978-3-030-61527-7_16
Autor:
Loïc Rollus, Renaud Hoyoux, Louis Wehenkel, Gilles Louppe, Benjamin Stevens, Pierre Geurts, Raphaël Marée, Philipp Kainz, Jean-Michel Begon, Rémy Vandaele
Publikováno v:
Bioinformatics
Motivation: Collaborative analysis of massive imaging datasets is essential to enable scientific discoveries. Results: We developed Cytomine to foster active and distributed collaboration of multidisciplinary teams for large-scale image-based studies
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1094e977134fa78173c40a21a24ad962
https://doi.org/10.1093/bioinformatics/btw013
https://doi.org/10.1093/bioinformatics/btw013