A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

Article Article scientifique Article A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences eng 2022-09-06 author Graziani Mara 0000-0003-3456-945X 897227 author Dutkiewicz Lidia author Calvaresi Davide author Amorim José Pereira author Yordanova Katerina author Vered Mor author Nair Rahul Ramachandran 813666 author Abreu Pedro Henriques author Blanke Tobias author Pulignano Valeria author Prior John O. author Lauwaert Lode author Reijers Wessel author Depeursinge Adrien 640343 author Andrearczyk Vincent author Muller Henning 126188 10.1007/s10462-022-10256-8 36092822 0269-2821 PMC9446618 https://link.springer.com/10.1007/s10462-022-10256-8 Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to conquer many technology products and their fields of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from different domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable , explainable and transparent being often used interchangeably in methodology papers. These words, however, convey different meanings and are “weighted" differently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efficiency in the definition of regulations for ethical and reliable AI development. We show how our taxonomy and definition of interpretable AI differ from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a—highly needed—standard for the communication among interdisciplinary areas of AI. Explainable artificial intelligence Interpretability Machine learning Dewey 616.0757 European Commission A European Excellence Centre for Media, Society and Democracy 951911 AI4Media EU H2020 European Commission Resolving Precariousness: Advancing the Theory and Measurement of Precariousness across the paid/unpaid work continuum 833577 REsPecTMe EU H2020 Hasler Foundation project numbers 2104 Fundação para a Ciência e a Tecnologia, I.P. Interpretable Personalized Models for Oncological Diseases: a deep methodology on how different cancers evolve SFRH/BD/136786/2018 SFRH/BD/136786/2018 PT FARH 62 Département de radiologie et informatique médicale 227 false 469 Radiologie des urgences 800 Artificial intelligence review bf590c2e-2fb1-48ad-a7a0-637ac88f4461 Article (Published version) Public Article-scientifique-from-crossref.pdf 1093483 application/pdf CC BY-4.0 openAccess Faculté de médecine / Section de médecine clinique / Département de radiologie et informatique médicale

Title	Published in	Access level	OA Policy	Year	Views	Downloads

A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences	Artificial intelligence review			2022	195	257

Archive ouverte UNIGE

Nair, Rahul Ramachandran