Stronger convergence results for deep residual networks: network width scales linearly with training data size (Q5095259)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Stronger convergence results for deep residual networks: network width scales linearly with training data size |
scientific article; zbMATH DE number 7569161
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Stronger convergence results for deep residual networks: network width scales linearly with training data size |
scientific article; zbMATH DE number 7569161 |
Statements
Stronger convergence results for deep residual networks: network width scales linearly with training data size (English)
0 references
5 August 2022
0 references
deep residual networks
0 references
neural tangent kernel
0 references
activation function
0 references
deep network optimization
0 references
