Approximation properties of some two-layer feedforward neural networks
Michał Nowak · DOAJ (DOAJ: Directory of Open Access Journals) · 2007
In this article, we present a multivariate two-layer feedforward neural networks that approximate continuous functions defined on \([0,1]^d\). We show that the \(L_1\) error of approximation is asymptotically proportional to the modulus of continuity of the underlying function taken at \(\sqrt{d}/n\), where \(n\) is the number of function values used.