Nonlinear approximation and (deep) ReLU networks (Q2117331): Difference between revisions
From MaRDI portal
Created a new Item |
Added link to MaRDI item. |
||
links / mardi / name | links / mardi / name | ||
Revision as of 23:42, 1 February 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Nonlinear approximation and (deep) ReLU networks |
scientific article |
Statements
Nonlinear approximation and (deep) ReLU networks (English)
0 references
21 March 2022
0 references
The authors address the approximation power of ReLU (rectified linear unit) networks and investigate whether such networks really provide a more powerful approximation efficiency than classical methods of approximation. The discussion of this question takes place in the univariate setting as there one has the best chance to obtain definitive results. The authors focus on the advantages of depth, i.e., what advantages are present in deep networks that do not appear in shallow networks.
0 references
neural networks
0 references
rectified linear unit (ReLU)
0 references
expressiveness
0 references
approximation power
0 references