QUANTITATIVE APPROXIMATION BY MULTIPLE SIGMOIDS KANTOROVICH-SHILKRET QUASI-INTERPOLATION NEURAL NETWORK OPERATORS

In this article, we derive multivariate quantitative approximation by Kantorovich-Shilkret type quasi-interpolation neural network operators with respect to supremum and L-p norms. This is done with rates using the multivariate modulus of continuity. We approximate continuous and bounded functions on R-N, N is an element of N. When they are also uniformly continuous, we have pointwise and uniform convergences, plus L-p estimates. We include also the related complex approximation. Our activation functions are induced by multiple general sigmoid functions.