Remarks and Prospects on Explainable Fuzzy Systems

Since 2016, there is an increasing interest on research topics such as fairness, accountability and interpretability, in the entire community of researchers in Artificial Intelligence. However, there were researchers working hard on these research topics much earlier. For example, Michalski published his comprehensibility postulate in the 1980s while Zadeh introduced the notions of fuzzy sets and systems in the 1960s and the paradigm of computing with words in the 1990s. Moreover, Zadeh was talking about precisiated natural language in 2004. All these pioneer contributions to explainable Artificial Intelligence should be recognized properly. Explainable fuzzy systems go a step ahead of interpretable fuzzy systems and are ready to act as a cornerstone in the context of explainable Artificial Intelligence where interdisciplinary research fields (e.g., Computational Linguistics, Argumentation Technology, Human-machine Interaction, Philosophy, Math, Computer Science, Neuroscience, and so on) meet. Explainable fuzzy systems provide users with interactive explanations in natural language, the preferred modality among humans, with visualization as a complementary modality. Fuzzy Logic endows explainable fuzzy systems with a solid mathematical background to model properly the inherent uncertainty, imprecision and vagueness of human language.