The Opaque Nature of Intelligence and the Pursuit of Explainable AI

Thomson, Sarah L.; van Stein, Niki; van den Berg, Daan; van Leeuwen, Cees

Abstract

When artificial intelligence is used for making decisions, people are more likely to accept those decisions if they can be made intelligible to the public. This understanding has led to the emerging field of explainable artificial intelligence. We review how research on explainable artificial intelligence is being conducted and discuss the limitations of current approaches. In addition to technical limitations, there is the huge problem that human decision-making is not entirely transparent either. We conclude with our position that the opacity of intelligent decision-making may be intrinsic, and with the larger question of whether we really need explanations for trusting inherently complex and large intelligent systems — artificial or otherwise.

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: NCTA 2023: 15th International Conference on Neural Computation Theory and Applications
• Start Date: Nov 13, 2023
• End Date: Nov 15, 2023
• Acceptance Date: Sep 27, 2023
• Publication Date: 2023
• Deposit Date: Sep 27, 2023
• Publisher: Scitepress Digital Library
• Pages: 555-564
• Book Title: Proceedings of the 15th International Joint Conference on Computational Intelligence
• ISBN: 978-989-758-674-3
• DOI: https://doi.org/10.5220/0012249500003595
• Keywords: Explainable Artificial Intelligence, XAI, Machine Learning, Neural Networks, Cognitive Science
• Public URL: http://researchrepository.napier.ac.uk/Output/3202393
• Related Public URLs: https://ncta.scitevents.org/