From knowledge-based to data-driven modeling of fuzzy rule-based systems: A critical reflection

This paper briefly elaborates on a development in (applied) fuzzy logic that has taken place in the last couple of decades, namely, the complementation or even replacement of the traditional knowledge-based approach to fuzzy rule-based systems design by a data-driven one. It is argued that the classical rule-based modeling paradigm is actually more amenable to the knowledge-based approach, for which it has originally been conceived, while being less apt to data-driven model design. An important reason that prevents fuzzy (rule-based) systems from being leveraged in large-scale applications is the flat structure of rule bases, along with the local nature of fuzzy rules and their limited ability to express complex dependencies between variables. This motivates alternative approaches to fuzzy systems modeling, in which functional dependencies can be represented more flexibly and more compactly in terms of hierarchical structures.