On the universal approximation property of radial basis function neural networks

Autor:	Ismayilova, Aysu, Ismayilov, Muhammad
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning 41A30 41A63 68T05 92B20
Druh dokumentu:	Working Paper
Popis:	In this paper we consider a new class of RBF (Radial Basis Function) neural networks, in which smoothing factors are replaced with shifts. We prove under certain conditions on the activation function that these networks are capable of approximating any continuous multivariate function on any compact subset of the $d$-dimensional Euclidean space. For RBF networks with finitely many fixed centroids we describe conditions guaranteeing approximation with arbitrary precision. Comment: 11 pages, a short proof of Theorem 3.3 added
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.02220 Zobrazit plný text záznamu View this record from Arxiv