Analyses of regular fuzzy neural networks for approximation capabilities

DOI10.1016/S0165-0114(98)00248-6MaRDI QIDQ1582670zbMATH OpenFDO

Authors Pu-yin Liu

Publication date 6 February 2001

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

Full work available at URL https://doi.org/10.1016/S0165-0114(98)00248-6

zbMATH Keywords

fuzzy neural networkstrapezoidal F functiontrapezoidal F numbersuniversal approximation

Mathematics Subject Classification ID

Approximations and expansions (41A99) Neural networks for/in biological studies, artificial life and related topics (92B20) Fuzzy control/observation systems (93C42)

Review text

Regular fuzzy neural networks (RFNNs) are proved to be the universal approximator to extended functions. By defining the multivariable trapezoidal F functions with extended addition of F numbers it is shown that the above conclusions hold for RFNNs with multi-input unit.

Recommendations

• Approximation of fuzzy functions by regular fuzzy neural networks
• Approximation capabilities of multilayer feedforward regular fuzzy neural networks
• Approximation capability of regular fuzzy neural networks to continuous fuzzy functions
• Universal approximation of three-layer regular fuzzy neural networks for a class of functions
• Can fuzzy neural nets approximate continuous fuzzy functions?

Cites work

• A note on the extension principle for fuzzy sets
• An Embedding Theorem for Spaces of Convex Sets
• Approximation by superpositions of a sigmoidal function
• Can fuzzy neural nets approximate continuous fuzzy functions?
• Characterization of compact subsets of fuzzy sets
• Differentials of fuzzy-valued functions and their applications to fuzzy neural networks
• Fuzzy input-output controllers are universal approximators
• scientific article; zbMATH DE number 1348985 (Why is no real title available?)
• Limit theorems for fuzzy random variables
• On the equivalence of neural nets and fuzzy expert systems
• Sugeno type controllers are universal controllers

Cited in

(16)

• Analysis of approximation of continuous fuzzy functions by multivariate fuzzy polynomials
• Approximation analysis of feedforward regular fuzzy neural network with two hidden layers
• Application of T-S fuzzy neural network based on declination compensation in soft sensing
• Approximation of level continuous fuzzy-valued functions by multilayer regular fuzzy neural networks
• Approximation capabilities of multilayer fuzzy neural networks on the set of fuzzy-valued functions
• scientific article; zbMATH DE number 5300444 (Why is no real title available?)
• Approximation of fuzzy functions by regular fuzzy neural networks
• Universal approximation of three-layer regular fuzzy neural networks for a class of functions
• Approximation of fuzzy neural networks based on Choquet integral
• THREE-PARAMETER FUZZY ARITHMETIC APPROXIMATION OF L-R FUZZY NUMBERS FOR FUZZY NEURAL NETWORKS
• Advances in Neural Networks – ISNN 2005
• Universal approximations of continuous fuzzy-valued functions by multi-layer regular fuzzy neural networks
• Approximation capabilities of multilayer feedforward regular fuzzy neural networks
• Numerical analysis of the learning of fuzzified neural networks from fuzzy if-then rules
• Approximation of fuzzy-valued functions by regular fuzzy neural networks and the accuracy analysis
• Analysis of artificial neural network learning near temporary minima: a fuzzy logic approach

This page was built for publication: Analyses of regular fuzzy neural networks for approximation capabilities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1582670)