IFS 2013 - Special Session on Interpretable Fuzzy Systems

Organizers: Corrado Mencar, Ciro Castiello, José M. Alonso, Luis Magdalena
The aim of this special session is to discuss and disseminate the most recent advancements focused on interpretability of fuzzy systems. Many fuzzy algorithms and models are indeed aimed at extracting knowledge from data, and the acquired knowledge must be usually communicated to users. However, as far as such knowledge is difficult to understand by users, the acceptance of such methods may be seriously compromised. Interpretability must be the central point on system modeling. In fact, some of the hottest and most recent research topics like Precisiated Natural Language, Computing With Words, and Human Centric Computing strongly rely on the interpretability of the designed models.
Interpretability is therefore a key property of intelligent systems of practical use, but its human-centric character poses difficult challenges both in design and evaluation. The topics of interest of this special session include (but are not limited to): Characterizations of interpretability; Learning methods for interpretable models; Interpretability evaluation and improvements; Relations between interpretability and other criteria (such as accuracy, stability, etc.); Design issues; Successful applications of interpretable fuzzy models; and so on.