modReLU

2000년 도입 · 논문 6편에서 사용

modReLU is an activation that is a modification of a ReLU. It is a pointwise nonlinearity, $\sigma\_{modReLU}\left(z\right) : C \rightarrow C$, which affects only the absolute value of a complex number, defined as: $$ \sigma\_{modReLU}\left(z\right) = \left(|z| + b\right)\frac{z}{|z|} \text{ if } |z| + b \geq 0 $$ $$ \sigma\_{modReLU}\left(z\right) = 0 \text{ if } |z| + b \leq 0 $$ where $b \in \mathbb{R}$ is a bias parameter of the nonlinearity. For a $n\_{h}$ dimensional hidden space we learn $n\_{h}$ nonlinearity bias parameters, one per dimension.

출처: Unitary Evolution Recurrent Neural Networks

소개 논문: Unitary Evolution Recurrent Neural Networks