| Título |
Two-hidden-layer feed-forward networks are universal approximators: A constructive approach |
| Autores |
PALUZO HIDALGO, EDUARDO, Gonzalez-Diaz, Rocio , Gutierrez-Naranjo, Miguel A. |
| Publicación externa |
Si |
| Medio |
Neural Networks |
| Alcance |
Article |
| Naturaleza |
Científica |
| Cuartil JCR |
1 |
| Cuartil SJR |
1 |
| Impacto JCR |
8.05 |
| Impacto SJR |
1.396 |
| Fecha de publicacion |
01/11/2020 |
| ISI |
000581746300003 |
| DOI |
10.1016/j.neunet.2020.07.021 |
| Abstract |
It is well-known that artificial neural networks are universal approximators. The classical existence result proves that, given a continuous function on a compact set embedded in an n-dimensional space, there exists a one-hidden-layer feed-forward network that approximates the function. In this paper, a constructive approach to this problem is given for the case of a continuous function on triangulated spaces. Once a triangulation of the space is given, a two-hidden-layer feed-forward network with a concrete set of weights is computed. The level of the approximation depends on the refinement of the triangulation. (C) 2020 Elsevier Ltd. All rights reserved. |
| Palabras clave |
Universal Approximation Theorem; Simplicial Approximation Theorem; Multi-layer feed-forward network; Triangulations |
| Miembros de la Universidad Loyola |
|
Gestionar cookies