Regularization

Euclidean Norm Regularization

Introduced by Wu et al. in Deep Compressed Sensing

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

Source: Deep Compressed Sensing

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Bias Detection 2 15.38%
Clustering 2 15.38%
Fairness 1 7.69%
Edge-computing 1 7.69%
Denoising 1 7.69%
Decision Making 1 7.69%
BIG-bench Machine Learning 1 7.69%
Computational Efficiency 1 7.69%
Conditional Image Generation 1 7.69%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories