SinLU: Sinu-Sigmoidal Linear Unit
Non-linear activation functions are integral parts of deep neural architectures. Given the large and complex dataset of a neural network, its computational complexity and approximation capability can differ significantly based on what activation function is used. Parameterizing an activation functio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/3/337 |