Viet-Anh on Software Logo

What is: Euclidean Norm Regularization?

SourceDeep Compressed Sensing
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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_rΔz2_2R\_{z} = w\_{r} \cdot ||\Delta{z}||^{2}\_{2}

where the scalar weight w_rw\_{r} is a parameter.

Image: LOGAN