dc.contributor.author | Cardaliaguet, Pierre | |
dc.contributor.author | Euvrard, Guillaume | |
dc.date.accessioned | 2014-12-18T08:39:41Z | |
dc.date.available | 2014-12-18T08:39:41Z | |
dc.date.issued | 1992 | |
dc.identifier.uri | https://basepub.dauphine.fr/handle/123456789/14468 | |
dc.language.iso | en | en |
dc.subject | Feedforward neural networks | en |
dc.subject | Functions approximation | en |
dc.subject | Interpolation | en |
dc.subject | Bell-shaped functions | en |
dc.subject | Squashing functions | en |
dc.subject | Robustness with respect to noise | en |
dc.subject | Implicit function | en |
dc.subject | Control | en |
dc.subject.ddc | 515 | en |
dc.title | Approximation of a function and its derivative with a neural network | en |
dc.type | Article accepté pour publication ou publié | |
dc.description.abstracten | This paper deals with the approximation of both a function and its derivative by feedforward neural networks. We propose an explicit formula of approximation which is noise resistant and can be easily modified with the patterns. We apply these results to approach a function defined implicitly, which is useful in control theory. | en |
dc.relation.isversionofjnlname | Neural Networks | |
dc.relation.isversionofjnlvol | 5 | en |
dc.relation.isversionofjnlissue | 2 | en |
dc.relation.isversionofjnldate | 1992 | |
dc.relation.isversionofjnlpages | 207-220 | en |
dc.relation.isversionofdoi | http://dx.doi.org/10.1016/S0893-6080(05)80020-6 | en |
dc.relation.isversionofjnlpublisher | Elsevier | en |
dc.subject.ddclabel | Analyse | en |
dc.relation.forthcoming | non | en |
dc.relation.forthcomingprint | non | en |