ShiLU
Shifted Rectified Linear Unit
2000년 도입 · 논문 1편에서 사용
The Shifted Rectified Linear Unit, or ShiLU, is a modification of ReLU activation function that has trainable parameters. $$ShiLU(x) = \alpha ReLU(x) + \beta$$
출처: Trainable Activations for Image Classification
소개 논문: Trainable Activations for Image Classification
Activation Functions · General