RT Journal Article
T1 Explainable Artificial Intelligence (XAI): 												Concepts, taxonomies, opportunities and challenges toward responsible AI
A1 Barredo Arrieta, Alejandro
A1 Díaz-Rodríguez, Natalia
A1 Del Ser, Javier
A1 Bennetot, Adrien
A1 Tabik, Siham
A1 Barbado, Alberto
A1 Garcia, Salvador
A1 Gil-Lopez, Sergio
A1 Molina, Daniel
A1 Benjamins, Richard
A1 Chatila, Raja
A1 Herrera, Francisco
AB In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
SN 1566-2535
YR 2020
FD 2020-06
LK https://hdl.handle.net/11556/3455
UL https://hdl.handle.net/11556/3455
LA eng
NO Barredo Arrieta , A , Díaz-Rodríguez , N , Del Ser , J , Bennetot , A , Tabik , S , Barbado , A , Garcia , S , Gil-Lopez , S , Molina , D , Benjamins , R , Chatila , R & Herrera , F 2020 , ' Explainable Artificial Intelligence (XAI) : Concepts, taxonomies, opportunities and challenges toward responsible AI ' , Information Fusion , vol. 58 , pp. 82-115 . https://doi.org/10.1016/j.inffus.2019.12.012
NO Publisher Copyright: © 2019
NO Alejandro Barredo-Arrieta, Javier Del Ser and Sergio Gil-Lopez would like to thank the Basque Government for the funding support received through the EMAITEK and ELKARTEK programs. Javier Del Ser also acknowledges funding support from the Consolidated Research Group MATHMODE ( IT1294-19 ) granted by the Department of Education of the Basque Government. Siham Tabik, Salvador Garcia, Daniel Molina and Francisco Herrera would like to thank the Spanish Government for its funding support (SMART-DaSCI project, TIN2017-89517-P ), as well as the BBVA Foundation through its Ayudas Fundación BBVA a Equipos de Investigación Científica 2018 call (DeepSCOP project). This work was also funded in part by the European Union’s Horizon 2020 research and innovation programme AI4EU under grant agreement 825619 . We also thank Chris Olah, Alexander Mordvintsev and Ludwig Schubert for borrowing images for illustration purposes. Part of this overview is inspired by a preliminary work of the concept of Responsible AI: R. Benjamins, A. Barbado, D. Sierra, “Responsible AI by Design”, to appear in the Proceedings of the Human-Centered AI: Trustworthiness of AI Models & Data (HAI) track at AAAI Fall Symposium, DC, November 7–9, 2019 [386] . Alejandro Barredo-Arrieta, Javier Del Ser and Sergio Gil-Lopez would like to thank the Basque Government for the funding support received through the EMAITEK and ELKARTEK programs. Javier Del Ser also acknowledges funding support from the Consolidated Research Group MATHMODE (IT1294-19) granted by the Department of Education of the Basque Government. Siham Tabik, Salvador Garcia, Daniel Molina and Francisco Herrera would like to thank the Spanish Government for its funding support (SMART-DaSCI project, TIN2017-89517-P), as well as the BBVA Foundation through its Ayudas Fundación BBVA a Equipos de Investigación Científica 2018 call (DeepSCOP project). This work was also funded in part by the European Union's Horizon 2020 research and innovation programme AI4EU under grant agreement 825619. We also thank Chris Olah, Alexander Mordvintsev and Ludwig Schubert for borrowing images for illustration purposes. Part of this overview is inspired by a preliminary work of the concept of Responsible AI: R. Benjamins, A. Barbado, D. Sierra, “Responsible AI by Design”, to appear in the Proceedings of the Human-Centered AI: Trustworthiness of AI Models & Data (HAI) track at AAAI Fall Symposium, DC, November 7–9, 2019 [386].
DS TECNALIA Publications
RD 31 jul 2024