L p approximation capability of RBF neural networks

Autor:	Dong Nan, Jin Ling Long, Yu Mei Ma, Lin Jun Sun, Wei Wu
Rok vydání:	2008
Předmět:	Discrete mathematics Polynomial Compact space Artificial neural network Applied Mathematics General Mathematics Activation function Radial basis function Function (mathematics) Algorithm Mathematics
Zdroj:	Acta Mathematica Sinica, English Series. 24:1533-1540
ISSN:	1439-7617 1439-8516
DOI:	10.1007/s10114-008-6423-x
Popis:	L p approximation capability of radial basis function (RBF) neural networks is investigated. If g: R + 1 → R 1 and $$ g(\parallel x\parallel _{R^n } ) $$ ∈ L loc (R n ) with 1 ≤ p < ∞, then the RBF neural networks with g as the activation function can approximate any given function in L p (K) with any accuracy for any compact set K in R n , if and only if g(x) is not an even polynomial.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d4bf22d40cc42d8fffd6936c3afafac5 https://doi.org/10.1007/s10114-008-6423-x Zobrazit plný text záznamu Plný text ve formátu PDF