Looking for a real-world-semantics-based approach to the interpretability of fuzzy systems
The existing studies of the interpretability of fuzzy systems have mainly focused on the analysis of the relation between a model of the fuzzy system and a human user considered as a beneficiary, i.e., a domain expert or a designer. Suggested by the concepts of "model" of formalized theories, "realization" of formalized language, and "interpretability" of a theory in another, this report presents a new approach to the fuzzy system interpretability. The new approach is grounded on the qualitative real-world semantics of words and relationships between the semantics of fuzzy system components and substructures of the real-world which the fuzzy systems are related to. Therefore, this approach is called real-world-semantics-based approach and it is aimed at characterizing the so-called real-world-semantics-based interpretability of fuzzy systems. It considers the actual semantics of all fuzzy system components, including the interpretability of the inference engine. Moreover, this new approach opens the door to a new way to study the interpretability of fuzzy systems.
keywords:
Publication: Congress
1624015044119
June 18, 2021
/research/publications/looking-for-a-real-world-semantics-based-approach-to-the-interpretability-of-fuzzy-systems
The existing studies of the interpretability of fuzzy systems have mainly focused on the analysis of the relation between a model of the fuzzy system and a human user considered as a beneficiary, i.e., a domain expert or a designer. Suggested by the concepts of "model" of formalized theories, "realization" of formalized language, and "interpretability" of a theory in another, this report presents a new approach to the fuzzy system interpretability. The new approach is grounded on the qualitative real-world semantics of words and relationships between the semantics of fuzzy system components and substructures of the real-world which the fuzzy systems are related to. Therefore, this approach is called real-world-semantics-based approach and it is aimed at characterizing the so-called real-world-semantics-based interpretability of fuzzy systems. It considers the actual semantics of all fuzzy system components, including the interpretability of the inference engine. Moreover, this new approach opens the door to a new way to study the interpretability of fuzzy systems. - Cat Ho Nguyen, Jose M. Alonso - 10.1109/FUZZ-IEEE.2017.8015562
publications_en