A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences.
Mara Graziani, Lidia Dutkiewicz, Davide Calvaresi, Jos�� Pereira Amorim, Katerina Yordanova, Mor Vered, Rahul Nair, Pedro Henriques Abreu, Tobias Blanke, Valeria Pulignano, John O Prior, Lode Lauwaert, Wessel Reijers, Adrien Depeursinge, Vincent Andrearczyk, Henning M��ller
Author Information
Mara Graziani: University of Applied Sciences of Western Switzerland (HES-SO Valais), Rue du Technopole 3, Sierre, 3960 Valais Switzerland. ORCID
Lidia Dutkiewicz: Centre for IT and IP Law, KU Leuven, Sint-Michielsstraat 6, Leuven, 3000 Belgium.
Davide Calvaresi: University of Applied Sciences of Western Switzerland (HES-SO Valais), Rue du Technopole 3, Sierre, 3960 Valais Switzerland.
Jos�� Pereira Amorim: CISUC, Department of Informatics Engineering, University of Coimbra, P��lo II, Pinhal de Marrocos, Coimbra, 3030-790 Portugal.
Katerina Yordanova: Centre for IT and IP Law, KU Leuven, Sint-Michielsstraat 6, Leuven, 3000 Belgium.
Mor Vered: Department of Data Science and AI, Monash University, Wellington Rd, Clayton VIC, Melbourne, 3800 Australia.
Rahul Nair: IBM Research Europe, 3 Technology Campus, Dublin, D15 HN66 Ireland.
Pedro Henriques Abreu: CISUC, Department of Informatics Engineering, University of Coimbra, P��lo II, Pinhal de Marrocos, Coimbra, 3030-790 Portugal.
Tobias Blanke: Institute of Logic, Language and Computation, University of Amsterdam, Spui 21, Amsterdam, 1012WX Netherlands.
Valeria Pulignano: Faculty of Social Science, Centre for Sociological Research, Parkstraat 45 bus, Leuven, 3000 Belgium.
John O Prior: Department of Nuclear Medicine and Molecular Imaging, Lausanne University Hospital, Rue du Bugnon 46, Lausanne, 1011 Vaud Switzerland.
Lode Lauwaert: Institute of Philosophy, KU Leuven, Kardinaal Mercierplein 2, bus 3200, Leuven, 3000 Belgium.
Wessel Reijers: Robert Schuman Centre, European University Institute, Via Boccaccio 121, Florence, 50133 Italy.
Adrien Depeursinge: University of Applied Sciences of Western Switzerland (HES-SO Valais), Rue du Technopole 3, Sierre, 3960 Valais Switzerland.
Vincent Andrearczyk: University of Applied Sciences of Western Switzerland (HES-SO Valais), Rue du Technopole 3, Sierre, 3960 Valais Switzerland.
Henning M��ller: University of Applied Sciences of Western Switzerland (HES-SO Valais), Rue du Technopole 3, Sierre, 3960 Valais Switzerland.
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 , and 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.
