Euclidean Norm Regularization

2000년 도입 · 논문 9편에서 사용

Euclidean Norm Regularization is a regularization step used in generative adversarial networks, and is typically added to both the generator and discriminator losses: $$ R\_{z} = w\_{r} \cdot ||\Delta{z}||^{2}\_{2} $$ where the scalar weight $w\_{r}$ is a parameter. Image: LOGAN

출처: Deep Compressed Sensing

소개 논문: Deep Compressed Sensing