Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces (Q6592113)
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 7900824
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces |
scientific article; zbMATH DE number 7900824 |
Statements
Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces (English)
0 references
24 August 2024
0 references
deep neural networks
0 references
approximation spaces
0 references
information based complexity
0 references
Gelfand numbers
0 references
theory-to-computational gaps
0 references
randomized approximation
0 references
0 references
0 references
0.8085699677467346
0 references
0.7952651381492615
0 references
0.7691969275474548
0 references
0.7493730187416077
0 references
0.7424471378326416
0 references
