NormLinComb

2000년 도입 · 논문 1편에서 사용

The Normalized Linear Combination of Activations, or NormLinComb, is a type of activation function that has trainable parameters and uses the normalized linear combination of other activation functions. $$NormLinComb(x) = \frac{\sum\limits_{i=0}^{n} w_i \mathcal{F}_i(x)}{\mid \mid W \mid \mid}$$

출처: Trainable Activations for Image Classification

소개 논문: Trainable Activations for Image Classification