Here we study further the multivariate quasi-interpolation of sigmoidal and hyperbolic tangent types neural network operators of one hidden layer. We derive multivariate Voronovskaya type asymptotic expansions for the error of approximation of these operators to the unit operator.
@article{1275, title = {Voronovskaya type asymptotic expansions for multivariate quasi-interpolation neural network operators}, journal = {CUBO, A Mathematical Journal}, volume = {16}, year = {2014}, language = {en}, url = {http://dml.mathdoc.fr/item/1275} }
Anastassiou, George. Voronovskaya type asymptotic expansions for multivariate quasi-interpolation neural network operators. CUBO, A Mathematical Journal, Tome 16 (2014) . http://gdmltest.u-ga.fr/item/1275/