A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences.
Fiche du document
2023
- doi: 10.1007/s10462-022-10256-8
- issn: 0269-2821
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1007/s10462-022-10256-8
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/pmid/36092822
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/pissn/0269-2821
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/urn/urn:nbn:ch:serval-BIB_F299B1AB6D9D1
info:eu-repo/semantics/openAccess , CC BY 4.0 , https://creativecommons.org/licenses/by/4.0/
Sujets proches
Terminology Social science Sciences, Social Human sciences Social studies Behavioral sciences Nomenclature Proper names TerminologyCiter ce document
M. Graziani et al., « A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences. », Serveur académique Lausannois, ID : 10.1007/s10462-022-10256-8
Métriques
Partage / Export
Résumé
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.