A global universality of two-layer neural networks with ReLU activations (Q2236407)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 7413384
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A global universality of two-layer neural networks with ReLU activations |
scientific article; zbMATH DE number 7413384 |
Statements
A global universality of two-layer neural networks with ReLU activations (English)
0 references
22 October 2021
0 references
Summary: In the present study, we investigate a universality of neural networks, which concerns a density of the set of two-layer neural networks in function spaces. There are many works that handle the convergence over compact sets. In the present paper, we consider a global convergence by introducing a norm suitably, so that our results will be uniform over any compact set.
0 references
0.7663476467132568
0 references
0.7638188004493713
0 references
0.7465845346450806
0 references
0.739531397819519
0 references
0.7361938953399658
0 references
