Published April 3, 2023
| Version v1
Publication
Two-hidden-layer feed-forward networks are universal approximators: A constructive approach
Description
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.
Additional details
- URL
- https://idus.us.es/handle//11441/143874
- URN
- urn:oai:idus.us.es:11441/143874
- Origin repository
- USE