Activation Normalization

2000년 도입 · 논문 61편에서 사용

Activation Normalization is a type of normalization used for flow-based generative models; specifically it was introduced in the GLOW architecture. An ActNorm layer performs an affine transformation of the activations using a scale and bias parameter per channel, similar to batch normalization. These parameters are initialized such that the post-actnorm activations per-channel have zero mean and unit variance given an initial minibatch of data. This is a form of data dependent initilization. After initialization, the scale and bias are treated as regular trainable parameters that are independent of the data.

출처: Glow: Generative Flow with Invertible 1x1 Convolutions

소개 논문: Glow: Generative Flow with Invertible 1x1 Convolutions