DOI: 10.7494/opmath.2007.27.1.59 ISSN: 1232-9274

Approximation properties of some two-layer feedforward neural networks

Michał A. Nowak
Show PDF Cite

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.

More from our Archive