Relaxed conditions for radial-basis function networks to be universal approximators.
From MaRDI portal
Publication:1422258
DOI10.1016/S0893-6080(02)00227-7zbMath1255.65044OpenAlexW1998242011WikidataQ44858646 ScholiaQ44858646MaRDI QIDQ1422258
Shu-Cherng Fang, Yi Liao, Henry L. W. Nuttle
Publication date: 9 February 2004
Published in: Neural Networks (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/s0893-6080(02)00227-7
Related Items
The universal approximation capabilities of cylindrical approximate identity neural networks, A comment on ``Relaxed conditions for radial-basis function networks to be universal approximators, The rate of approximation of Gaussian radial basis neural networks in continuous function space, Using radial basis function networks for function approximation and classification, \(L^p\) approximation capability of RBF neural networks, Control of robots using radial basis function neural networks with dead-zone, The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks, Stochastic stability of a neural-net robot controller subject to signal-dependent noise in the learning rule, Multilayer perceptrons as function approximators for analytical solutions of the diffusion equation, Radial basis function neural networks of Hankel translates as universal approximators, On a problem of Hornik
Uses Software
Cites Work
