Legal requirements on explainability in machine learning

Autor:	Benoît Frénay, Adrien Bibal, Alexandre de Streel, Michael Lognoul
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	Computer science business.industry Deep learning Legal aspects of computing Context (language use) Machine learning computer.software_genre Explainability Artificial Intelligence Interpretability Philosophy of law Artificial intelligence Public decision making business computer Law
Zdroj:	Bibal, A, Lognoul, M, De Streel, A & Frénay, B 2021, ' Legal requirements on explainability in machine learning ', Artificial Intelligence & Law, vol. 29, no. 2, pp. 149-169 . https://doi.org/10.1007/s10506-020-09270-4, https://doi.org/10.1007/s10506-020-09270-4
ISSN:	1572-8382
DOI:	10.1007/s10506-020-09270-4
Popis:	Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9f9fc2f7df2890446cf568becc541f4 https://researchportal.unamur.be/en/publications/a4f56988-41d8-4f7b-9229-47abe7f51a2c Zobrazit plný text záznamu Full text from SpringerLink