Explainable AI: The New 42?

By Randy Goebel, Ajay Chander, Katharina Holzinger, Freddy Lécué, Zeynep Akata, Simone Stumpf, Peter Kieseberg, Andreas Holzinger. 2018

298 citations recorded by the source corpus.

Explainable AI is not a new field. Since at least the early exploitation of C.S. Pierce’s abductive reasoning in expert systems of the 1980s, there were reasoning architectures to support an explanation function for complex AI systems, including applications in medical diagnosis, complex multi-component design, and reasoning about the real world. So explainability is at least as old as early AI, and a natural consequence of the design of AI systems. While early expert systems consisted of handcrafted knowledge bases that enabled reasoning over narrowly well-defined domains (e.g., INTERNIST, MYCIN), such systems had no learning capabilities and had only primitive uncertainty handling. But the evolution of formal reasoning architectures to incorporate principled probabilistic reasoning helped address the capture and use of uncertain knowledge.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Informativeness [5, 44, 21, 25, 26, 45, 30, 32, 34, 35, 37, 38, 41, 46, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 63, 64, 65, 66, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 86, 87, 88, 89, 59, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 1”
Fairness of artificial intelligence in healthcare: review and recommendations (2023, unknown): “To enhance the accountability of AI, developing interpretable algorithms, visualizing decision‑making processes, and provid‑ ing comprehensible explanations for AI predictions are important [103].”
Causability and explainability of artificial intelligence in medicine (2019, methodology): “For more details on the theory behind scientific explainability we refer to the principles of abductive reasoning (Ma et al., 2010) and point to some current work (Babiker & Goebel, 2017; Goebel et al., 2018).”
Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study (2020, unknown): “In order to provide an interpretable overview (in the sense of eXplainable AI [17] ) of the predictive models that we developed, we also developed a Decision All rights reserved.”
Efficient Inference of Optimal Decision Trees (2020, background): “XAI has been the subject of several studies (Goebel et al. 2018; Li et al. 2018; Van Lent, Fisher, and Mancuso 2004; Angelino et al. 2017), and several events (IJCAI XAI Work-shop; NIPS IML Symposium; ACM FAT*).”
Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics (2021, background): “…since the launch of the USA’s Defense Advanced Research Projects Agency (DARPA) initiative [12], from the international research community [13–16] and to various application domains in recent years [17–19], which can be demonstrated by the enormous and quickly growing research publications…”
Benchmarking and survey of explanation methods for black box models (2021, background): “The widespread need for XAI in the last years caused an explosion of interest in the design of explanation methods (Goebel et al. 2018).”