Flexible and context-specific AI explainability: a multidisciplinary approach

V Beaudouin, I Bloch, D Bounie, S Clémençon… - arXiv preprint arXiv …, 2020 - arxiv.org
The recent enthusiasm for artificial intelligence (AI) is due principally to advances in deep
learning. Deep learning methods are remarkably accurate, but also opaque, which limits …

Explainable artificial intelligence: a comprehensive review

D Minh, HX Wang, YF Li, TN Nguyen - Artificial Intelligence Review, 2022 - Springer
Thanks to the exponential growth in computing power and vast amounts of data, artificial
intelligence (AI) has witnessed remarkable developments in recent years, enabling it to be …

Do explanations reflect decisions? A machine-centric strategy to quantify the performance of explainability algorithms

ZQ Lin, MJ Shafiee, S Bochkarev, MS Jules… - arXiv preprint arXiv …, 2019 - arxiv.org
There has been a significant surge of interest recently around the concept of explainable
artificial intelligence (XAI), where the goal is to produce an interpretation for a decision made …

[PDF][PDF] Towards quantification of explainability in explainable artificial intelligence methods

SR Islam, W Eberle, SK Ghafoor - The thirty-third international flairs …, 2020 - cdn.aaai.org
Artificial Intelligence (AI) has become an integral part of domains such as security, finance,
healthcare, medicine, and criminal justice. Explaining the decisions of AI systems in human …

Explainability fact sheets: a framework for systematic assessment of explainable approaches

K Sokol, P Flach - Proceedings of the 2020 conference on fairness …, 2020 - dl.acm.org
Explanations in Machine Learning come in many forms, but a consensus regarding their
desired properties is yet to emerge. In this paper we introduce a taxonomy and a set of …

Varieties of AI explanations under the law. From the GDPR to the AIA, and beyond

P Hacker, JH Passoth - … workshop on extending explainable AI beyond …, 2020 - Springer
The quest to explain the output of artificial intelligence systems has clearly moved from a
mere technical to a highly legally and politically relevant endeavor. In this paper, we provide …

Opportunities and challenges in explainable artificial intelligence (xai): A survey

A Das, P Rad - arXiv preprint arXiv:2006.11371, 2020 - arxiv.org
Nowadays, deep neural networks are widely used in mission critical systems such as
healthcare, self-driving vehicles, and military which have direct impact on human lives …

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

AB Arrieta, N Díaz-Rodríguez, J Del Ser, A Bennetot… - Information fusion, 2020 - Elsevier
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 …

One explanation does not fit all: A toolkit and taxonomy of ai explainability techniques

V Arya, RKE Bellamy, PY Chen, A Dhurandhar… - arXiv preprint arXiv …, 2019 - arxiv.org
As artificial intelligence and machine learning algorithms make further inroads into society,
calls are increasing from multiple stakeholders for these algorithms to explain their outputs …

A practical tutorial on explainable AI techniques

A Bennetot, I Donadello, A El Qadi El Haouari… - ACM Computing …, 2021 - dl.acm.org
The past years have been characterized by an upsurge in opaque automatic decision
support systems, such as Deep Neural Networks (DNNs). Although DNNs have great …