A FORMULA FOR THE APPROXIMATION OF FUNCTIONS BY SINGLE HIDDEN LAYER NEURAL NETWORKS WITH WEIGHTS FROM TWO STRAIGHT LINES
Proceedings of the Institute of Mathematics and Mechanics National Academy of Sciences of Azerbaijan · 2022
In this paper we consider approximation of a continuous function by single hidden layer neural networks with an arbitrary nonpolynomial activation function and with weights varying on two fixed straight lines.We obtain a formula for the approximation error.