TY  - JOUR
ID  - Nowak2007
LB  - Nowak2007
AU  - Nowak, Michał A.
TI  - Approximation properties of some two-layer feedforward neural networks
ST  - Approximation properties of some two-layer feedforward neural networks
JO  - Opuscula Math.
JA  - Opuscula Math.
JF  - Opuscula Mathematica
PY  - 2007
VL  - 27
IS  - 1
SP  - 59
EP  - 72
DO  - http://dx.doi.org/10.7494/OpMath.2007.27.1.59
UR  - http://dx.doi.org/10.7494/OpMath.2007.27.1.59
AB  - 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.
KW  - neural networks
KW  - approximation of functions
KW  - sigmoidal function
SN  - 1232-9274
ER  -