Wide neural networks of any depth evolve as linear models under gradient descent <sup>*</sup> (Q5857449): Difference between revisions
From MaRDI portal
Set OpenAlex properties. |
ReferenceBot (talk | contribs) Changed an Item |
||
| Property / cites work | |||
| Property / cites work: Q4452862 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: A mean field view of the landscape of two-layer neural networks / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Gradient descent optimizes over-parameterized deep ReLU networks / rank | |||
Normal rank | |||
Revision as of 21:47, 24 July 2024
scientific article; zbMATH DE number 7330523
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Wide neural networks of any depth evolve as linear models under gradient descent <sup>*</sup> |
scientific article; zbMATH DE number 7330523 |
Statements
Wide neural networks of any depth evolve as linear models under gradient descent <sup>*</sup> (English)
0 references
1 April 2021
0 references
machine learning
0 references
