Paving the way to explainable Artificial Intelligence with fuzzy modeling

TítuloPaving the way to explainable Artificial Intelligence with fuzzy modeling
AutoresC. Mencar, Jose M. Alonso
TipoCapítulo de libro
Fonte WILF2018 - 12th International Workshop on Fuzzy Logic and Applications, Springer, pp. 215-227 , 2019.
ISBN978-3-030-12543-1
DOI10.1007/978-3-030-12544-8_17
AbstractExplainable Artificial Intelligence (XAI) is a relatively new approach to AI with special emphasis to the ability of machines to give sound motivations about their decisions and behavior. Since XAI is human-centered, it has tight connections with Granular Computing (GrC) in general, and Fuzzy Modeling (FM) in particular. However, although FM has been originally conceived to provide easily understandable models to users, this property cannot be taken for grant but it requires careful design choices. Furthermore, full integration of FM into XAI requires further processing, such as Natural Language Generation (NLG), which is a matter of current research.