Universal approximations of continuous fuzzy-valued functions by multi-layer regular fuzzy neural networks

DOI10.1016/S0165-0114(99)00132-3MaRDI QIDQ5931181zbMATH OpenFDO

Publication date 8 January 2002

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

Full work available at URL https://doi.org/10.1016/S0165-0114(99)00132-3

fuzzy neural networks fuzzy-valued functions universal approximator

Approximation by other special function classes (41A30) Neural networks for/in biological studies, artificial life and related topics (92B20) Fuzzy control/observation systems (93C42)

Review text

The study is concerned with the approximation capabilities of fuzzy neural networks with numerical inputs and fuzzy connections in relation to continuous fuzzy-valued functions \(F\). More specifically, \(F:\mathbb{R}\to F(\mathbb{R})\) where \(F(\mathbb{R})\) denotes a family of fuzzy numbers in \(\mathbb{R}\) (namely, fuzzy sets whose \(\alpha\)-cuts are closed intervals in \(\mathbb{R}\), with bounded support and normal membership functions). One studies a neural network governed by the expression NEWLINE\[NEWLINEY= \sum^n_{i=1} W_i\Biggl(\sum^m_{j=1} V_{ij} \sigma(xU_j+ \Theta_j)\Biggr)NEWLINE\]NEWLINE whose connections (\(W_i,V_{ij}, U_j\) and \(\Theta_j\)) are regarded as fuzzy numbers with \(\sigma\) being a continuous monotonic function from \(\mathbb{R}\) to \(\mathbb{R}\), and ``\(n\) and ``\(m\) denoting the number of the nodes in the respective layers. It is shown that this network is a universal approximator of \(F\).

Recommendations

Cites work

Cited in

(21)

This page was built for publication: Universal approximations of continuous fuzzy-valued functions by multi-layer regular fuzzy neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5931181)