AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks

Zhaodong Chen, Lei Deng, Bangyan Wang, Guoqi Li, Yuan Xie

TPAMI 2020 · Architectures and efficiency › RNNs and normalization · approach: Weight normalization and decay interplay · 34 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
use leaky ReLU gamma=0.18 instead of ReLUGaussian-init serial net · CIFAR-10test accuracy: +2.83%Improved
raise leaky ReLU slope from 0.18 to 0.5 under BN (ablation)leaky ReLU serial net · CIFAR-10test accuracy: +0.59%Mixed
replace PReLU with sPReLU on delta orthogonal weightsserial net · CIFAR-10test accuracy: +7.73%Improved
use SeLU eps=0.03 instead of original configSeLU serial net · CIFAR-10test accuracy: +0.42% and +0.39%Improved
compute second moment from pre-activations (SMN) instead of weights (sWS) (ablation)normalization serial net · CIFAR-10test accuracy: 88.06% -> 88.50%Improved
use SMN instead of BNDenseNet · CIFAR-10test accuracy: 92.10% -> 92.06%No clear effect
add mixup to SMN (ablation)ResNet-56 · CIFAR-10test accuracy: 93.28% -> 93.93%Improved
use Fixup p=1.5 instead of p=2 (ablation)Fixup ResNet-56 with b&s and mixup · CIFAR-10test accuracy: 93.93% -> 94.28%Improved
use SeLU eps=0.06 instead of original SeLUConv MobileNet V1 · ImageNettop-1 error: Explode in the first epoch -> 30.37%Improved
use SeLU eps=0.03 instead of 0.06 (ablation)Conv MobileNet V1 · ImageNettop-1 error: 30.37% -> 30.87%Hurt
use leaky ReLU 0.3 instead of ReLU, GaussianConv MobileNet V1 · ImageNettop-1 error: 31.16% -> 29.39%Improved
add mixup to SMN (ablation)ResNet-50 · ImageNettop-1 error: 24.90% -> 23.74%Improved

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