Statements (20)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:activation_function
|
| gptkbp:abbreviation |
gptkb:ELU
|
| gptkbp:contrastsWith |
gptkb:ReLU
gptkb:Leaky_ReLU gptkb:Parametric_ReLU |
| gptkbp:differentiable |
yes
|
| gptkbp:form |
x if x > 0, alpha*(exp(x)-1) if x <= 0
|
| gptkbp:introduced |
gptkb:Djork-Arné_Clevert
2015 |
| gptkbp:output_range |
(-alpha, infinity)
|
| gptkbp:parameter |
alpha
|
| gptkbp:publishedIn |
gptkb:arXiv:1511.07289
|
| gptkbp:purpose |
improve learning characteristics of neural networks
|
| gptkbp:reduces |
vanishing gradient problem
|
| gptkbp:used_in |
convolutional neural networks
deep learning feedforward neural networks |
| gptkbp:bfsParent |
gptkb:ReLU
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Exponential Linear Unit
|