The Estimate for Approximation Error of Neural Network with Two Weights

Abstract

The neural network with two weights is constructed and its approximation ability to any continuous functions is proved. For this neural network, the activation function is not confined to the odd functions. We prove that it can limitlessly approach any continuous function from limited close subset of R(m) to R(n) and any continuous function, which has limit… (More)
DOI: 10.1155/2013/935312

Topics

Figures and Tables

Sorry, we couldn't extract any figures or tables for this paper.

Slides referencing similar topics