Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean (Q6077039)
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 7751448
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean |
scientific article; zbMATH DE number 7751448 |
Statements
Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean (English)
0 references
17 October 2023
0 references
deep neural networks
0 references
vanishing gradient
0 references
weights initialization
0 references
logistic activation function
0 references
supervised learning
0 references
0 references
0.7234834432601929
0 references
0.7149474620819092
0 references
0.6970596313476562
0 references
