Abstract
The issue of matching two fuzzy sets emerges as an essential design aspect in many algorithms of processing fuzzy information including fuzzy controllers, pattern classifiers, knowledge-based systems, etc. This paper introduces a new model of matching. The primordial features of the proposed model involve:
1.
(i) matching being carried out with respect to the grades of membership of the discussed fuzzy sets as well as some of their functionals (like energy, entropy, transom);
2.
(ii) the concepts of hierarchies of matching in the model leading directly to a straightforward distinction between “local” and “global” levels of matching; and
3.
(iii) a distributed character of the model that is realized as a logic-based neural network with enhanced learning capabilities.