PubMed · 9117896
Neural networks for functional approximation and system identification.
Abstract
We construct generalized translation networks to approximate uniformly a class of nonlinear, continuous functionals defined on Lp ([-1, 1]s) for integer s > or = 1, 1 < or = p < infinity, or C ([-1, 1]s). We obtain lower bounds on the possible order of approximation for such functionals in terms of any approximation process depending continuously on a given number of parameters. Our networks almost achieve this order of approximation in terms of the number of parameters (neurons) involved in the network. The training is simple and noniterative; in particular, we avoid any optimization such as that involved in the usual backpropagation.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
H N Mhaskar, N Hahm. 1997-01-01. Neural networks for functional approximation and system identification.. https://doi.org/10.1162/neco.1997.9.1.143. https://pubmed.health/record/pubmed%3A9117896/neural-networks-for-functional-approximation-and-system-identification
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite PubMed Health by Indiciae: BibTeX · RIS.