AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

New Interpretations of Normalization Methods in Deep Learning

Jiacheng Sun, Xiangyong Cao, Hanwen Liang, Weiran Huang, Zewei Chen, Zhenguo Li

AAAI 2020 · Architectures and efficiency › RNNs and normalization · approach: Batch normalization improvements · 42 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add weight decay to BNBN with ResNet-101 · CIFAR-10, Gaussian Noisetest accuracy: 0.8125 -> 0.7812Hurt
add weight decay to BNBN with ResNet-101 · CIFAR-10, BIM-$l_\infty$test accuracy: 0.5380 -> 0.6000Improved
add weight decay to BNBN with ResNet-101 · CIFAR-100, Gaussian Noisetest accuracy: 0.4596 -> 0.4953Improved
add weight decay to BNBN with ResNet-101 · CIFAR-100, BIM-$l_\infty$test accuracy: 0.1397 -> 0.1558Improved
add weight decay to normalization trainingBN, GN, LN, and WN · CIFAR-10 and CIFAR-100 under Gaussian noise and BIM attackstest accuracyMixed
train with a scaling-invariant normalization methodBN, LN, GN, or WN · CIFAR-10 and CIFAR-100adversarial robustnessHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy