Effects of depth, width, and initialization: a convergence analysis of layer-wise training for deep linear neural networks (Q5037872)
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: Effects of depth, width, and initialization: a convergence analysis of layer-wise training for deep linear neural networks |
scientific article; zbMATH DE number 7484162
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Effects of depth, width, and initialization: a convergence analysis of layer-wise training for deep linear neural networks |
scientific article; zbMATH DE number 7484162 |
Statements
Effects of depth, width, and initialization: A convergence analysis of layer-wise training for deep linear neural networks (English)
0 references
4 March 2022
0 references
deep linear neural networks
0 references
layer-wise training
0 references
block coordinate gradient descent
0 references
0 references
0.7138404250144958
0 references
0.7013614773750305
0 references
0.6972294449806213
0 references
0.6917617321014404
0 references
0.6912702918052673
0 references
