A three layer neural network can represent any multivariate function
Abstract
In 1987, Hecht-Nielsen showed that any continuous multivariate function can be implemented by a certain type three-layer neural network. This result was very much discussed in neural network literature. In this paper we prove that not only continuous functions but also all discontinuous functions can be implemented by such neural networks.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2020
- DOI:
- 10.48550/arXiv.2012.03016
- arXiv:
- arXiv:2012.03016
- Bibcode:
- 2020arXiv201203016I
- Keywords:
-
- Computer Science - Machine Learning;
- Mathematics - Functional Analysis;
- Statistics - Machine Learning;
- 26B40;
- 46A22;
- 46E10;
- 46N60;
- 68T05;
- 92B20
- E-Print:
- 9 pages