TY - JOUR
T1 - Explainable Artificial Intelligence (XAI)
T2 - Concepts, taxonomies, opportunities and challenges toward responsible AI
AU - Barredo Arrieta, Alejandro
AU - Díaz-Rodríguez, Natalia
AU - Del Ser, Javier
AU - Bennetot, Adrien
AU - Tabik, Siham
AU - Barbado, Alberto
AU - Garcia, Salvador
AU - Gil-Lopez, Sergio
AU - Molina, Daniel
AU - Benjamins, Richard
AU - Chatila, Raja
AU - Herrera, Francisco
N1 - Publisher Copyright:
© 2019
PY - 2020/6
Y1 - 2020/6
N2 - 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.
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.
KW - Accountability
KW - Comprehensibility
KW - Data Fusion
KW - Deep Learning
KW - Explainable Artificial Intelligence
KW - Fairness
KW - Interpretability
KW - Machine Learning
KW - Privacy
KW - Responsible Artificial Intelligence
KW - Transparency
UR - http://www.scopus.com/inward/record.url?scp=85077515399&partnerID=8YFLogxK
U2 - 10.1016/j.inffus.2019.12.012
DO - 10.1016/j.inffus.2019.12.012
M3 - Article
AN - SCOPUS:85077515399
SN - 1566-2535
VL - 58
SP - 82
EP - 115
JO - Information Fusion
JF - Information Fusion
ER -