Fuzzy systems with overlapping Gaussian concepts: Approximation properties in Sobolev norms

DOI10.1016/S0165-0114(01)00083-5MaRDI QIDQ1855477zbMATH OpenFDO

Authors Riccardo Rovatti, Giancarlo Ferrari-Trecate

Publication date 5 February 2003

Published in Fuzzy Sets and Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0165-0114(01)00083-5

zbMATH Keywords

approximationderivativesfuzzy system modelslearningneuro-fuzzy systemsradial basis functionsreproducing kernel Hilbert spaces

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Fuzzy control/observation systems (93C42)

Review text

The approximating capabilities of fuzzy systems with overlapping Gaussian concepts are considered. The target function is assumed to be sampled either on a regular grid or according to a uniform probability density. By exploiting a connection with radial basis functions approximators, a new method for the computation of the system coefficients is provided, showing that it guarantees uniform approximation of the derivatives of the target function.

Recommendations

• Fuzzy systems as universal approximators
• Consistent Sobolev regression via fuzzy systems with overlapping concepts
• Fuzzy systems are universal approximators for a smooth function and its derivatives
• scientific article; zbMATH DE number 2203931
• scientific article; zbMATH DE number 5917217

Cites work

• Consistent identification of NARX models via regularization networks
• Fuzzy systems as universal approximators
• scientific article; zbMATH DE number 3179593 (Why is no real title available?)
• scientific article; zbMATH DE number 45848 (Why is no real title available?)
• Practical Approximate Solutions to Linear Operator Equations When the Data are Noisy
• Regularization algorithms for learning that are equivalent to multilayer networks
• Theory of Reproducing Kernels
• Universal fuzzy controllers

Cited in

(3)

• Kernel shapes of fuzzy sets in fuzzy systems for function approximation
• Consistent Sobolev regression via fuzzy systems with overlapping concepts
• Function approximation using non-normalized SISO fuzzy systems

This page was built for publication: Fuzzy systems with overlapping Gaussian concepts: Approximation properties in Sobolev norms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1855477)