Two-hidden-layer feed-forward networks are universal approximators: A constructive approach

Authors:

Publisher website

1 November 2020

journal article
research article
Published by Elsevier in Neural Networks

Vol. 131, 29-36
DOI:10.1016/j.neunet.2020.07.021
PMID:32739651

Abstract

No abstract available

Keywords

All Related Versions

This publication has 5 references indexed in Scilit:

Geometric and Topological Inference
2018
On the approximation by single hidden layer feedforward neural networks with fixed weights
Neural Networks, 2018
Approximation capabilities of multilayer feedforward networks
Neural Networks, 1991
Approximation by superpositions of a sigmoidal function
Mathematics of Control, Signals, and Systems, 1989
Multilayer feedforward networks are universal approximators
Neural Networks, 1989