XAI: a Natural Application Domain for Fuzzy Set Theory

Bernadette Bouchon-Meunier (1) , Anne Laurent (2) , Marie-Jeanne Lesot (1)

1 LFI - Learning, Fuzzy and Intelligent systems
2 LIRMM | WEB3 - WEB Architecture x Semantic WEB x WEB of Data

As digital systems cover all personal and professional activities, artificial intelligence is now everywhere. In this context, it is crucial for systems and decisions to be understandable for humans, in a human-in-the-loop process. This global objective is known as eXplainable Artificial Intelligence (XAI). In this chapter, we argue that fuzzy logic is a key concept for XAI as it offers a theoretical framework that is closer than many others to human cognition, human reasoning and human intuitions. We exemplify the many advantages fuzzy logic offers to the XAI domain.

Mots clés: Fuzzy logic; Artificial Intelligence; Explainable AI (XAI); Computing With Words; Machine Learning; Approximate Reasoning

Domaines: Intelligence artificielle [cs.AI]

Bernadette Bouchon-Meunier, Anne Laurent, Marie-Jeanne Lesot. XAI: a Natural Application Domain for Fuzzy Set Theory. Alice E. Smith (ed.). Women in Computational Intelligence, Key Advances and Perspectives on Emerging Topics, Springer, pp.23-49, 2022, Women in Engineering and Science (WES), 978-3-030-79091-2. ⟨10.1007/978-3-030-79092-9_2⟩. ⟨hal-03501009⟩