Interpretability, complexity, and modular structure of fuzzy systems

MaRDI QIDQ4437868zbMATH OpenFDO

Authors M. Bikdash

Publication date 2003

zbMATH Keywords

complexitydifferentiabilityinterpretabilitylocal supportmembership functionsspline functionsTaylor series expansion

Mathematics Subject Classification ID

Numerical computation using splines (65D07) System structure simplification (93B11) Fuzzy control/observation systems (93C42)

Review text

In order to alleviate some fundamental interpretation problems in fuzzy sets applications, the author proposes a new principle which, loosely speaking, states that as the complexity of a system increases, one should impose additional structure on its definition to increase our ability to make precise and significant statements on its dynamics. As an example of such additional structure, it is argued that membership functions which are local in support and sufficiently differentiable exhibit high interpretability. One example of such membership functions are spline functions. This structure leads to the interpretation of every consequent polynomial as a Taylor series expansion. For the entire collection see [Zbl 1015.00012].

Recommendations

• scientific article; zbMATH DE number 6027033
• On interpretability of fuzzy models
• Interpretability issues in data-based learning of fuzzy systems
• Adaptability, interpretability and rule weights in fuzzy rule-based systems
• A formal model of interpretability of linguistic variables

Cited in

(1)

• Interpretability in fuzzy systems optimization: a topological approach

This page was built for publication: Interpretability, complexity, and modular structure of fuzzy systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4437868)