Representations and rates of approximation of real-valued Boolean functions by neural networks
Status PubMed-not-MEDLINE Language English Country United States Media print
Document type Journal Article
PubMed
12662803
DOI
10.1016/s0893-6080(98)00039-2
PII: S0893608098000392
Knihovny.cz E-resources
- Publication type
- Journal Article MeSH
We give upper bounds on rates of approximation of real-valued functions of d Boolean variables by one-hidden-layer perceptron networks. Our bounds are of the form c/n where c depends on certain norms of the function being approximated and n is the number of hidden units. We describe sets of functions where these norms grow either polynomially or exponentially with d.
References provided by Crossref.org
