On large batch training and sharp minima: a Fokker-Planck perspective (Q828491): Difference between revisions
From MaRDI portal
Changed an Item |
Changed an Item |
||
| Property / describes a project that uses | |||
| Property / describes a project that uses: AlexNet / rank | |||
Normal rank | |||
Revision as of 16:23, 28 February 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | On large batch training and sharp minima: a Fokker-Planck perspective |
scientific article |
Statements
On large batch training and sharp minima: a Fokker-Planck perspective (English)
0 references
8 January 2021
0 references
large batch training
0 references
sharp minima
0 references
Fokker-Planck equation
0 references
stochastic gradient algorithm
0 references
deep neural network
0 references
