White Paper Machine Learning in Certified Systems
Abstract
Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc. It is also an opportunity to implement and embed new capabilities out of the reach of classical implementation techniques. However, ML techniques introduce new potential risks. Therefore, they have only been applied in systems where their benefits are considered worth the increase of risk. In practice, ML techniques raise multiple challenges that could prevent their use in systems submitted to certification constraints. But what are the actual challenges? Can they be overcome by selecting appropriate ML techniques, or by adopting new engineering or certification practices? These are some of the questions addressed by the ML Certification 3 Workgroup (WG) set-up by the Institut de Recherche Technologique Saint Exup\'ery de Toulouse (IRT), as part of the DEEL Project.
Cite
@article{arxiv.2103.10529,
title = {White Paper Machine Learning in Certified Systems},
author = {Hervé Delseny and Christophe Gabreau and Adrien Gauffriau and Bernard Beaudouin and Ludovic Ponsolle and Lucian Alecu and Hugues Bonnin and Brice Beltran and Didier Duchel and Jean-Brice Ginestet and Alexandre Hervieu and Ghilaine Martinez and Sylvain Pasquet and Kevin Delmas and Claire Pagetti and Jean-Marc Gabriel and Camille Chapdelaine and Sylvaine Picard and Mathieu Damour and Cyril Cappi and Laurent Gardès and Florence De Grancey and Eric Jenn and Baptiste Lefevre and Gregory Flandin and Sébastien Gerchinovitz and Franck Mamalet and Alexandre Albore},
journal= {arXiv preprint arXiv:2103.10529},
year = {2021}
}
Comments
113 pages, White paper