AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Rethinking skip connection model as a learnable Markov chain

Dengsheng Chen, Jie Hu, Wenwen Qiang, Xiaoming Wei, Enhua Wu

ICLR 2023 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 2 citations (OpenAlex)

Read the paper

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 penal connection to TransformerTransformer · WMT-16 DE/EN and EN/DE, Q and SPPL: 33.3 -> 7.9; 17.3 -> 11.3; 31.8 -> 6.3; 13.4 -> 8.5Improved
Add penal connection to TransformerTransformer · WMT-16 DE/EN and EN/DE, Q and Saccuracy: 36.4 -> 70.0; 66.4 -> 70.4; 43.1 -> 71.8; 68.7 -> 72.8Improved
Add penal connection with τ=3×10⁻⁸ResNet50 · ImageNet-1K valtop-1 accuracy: 79.2 -> 79.4Improved
Add penal connection with τ=3×10⁻⁸ViT-S/16-224 · ImageNet-1K valtop-1 accuracy: 77.8 -> 78.1Improved
Add penal connection with τ=3×10⁻⁸DeIT-S/16-224 · ImageNet-1K valtop-1 accuracy: 79.9 -> 80.1Improved
Add penal connection with τ=3×10⁻⁸Swin-S/4-7-224 · ImageNet-1K valtop-1 accuracy: 83.3 -> 83.5Improved
Vary penal connection strength τ (ablation)ImageNet classification architectures · ImageNet-1K valtop-1 accuracy: ResNet50: 79.0, 79.4, 79.2, 79.3; ViT-S/16-224: 78.0, 78.1, 78.0, 77.8; DeIT-S/16-224: 79.9, 80.1, 80.0, 79.8; Swin-S/4-Mixed
Add penal connection to ResNetResNet · CIFAR10 and CIFAR100 at tested depthsaccuracy: CIFAR10: 92.1 -> 92.3; 92.6 -> 93.2; 93.2 -> 93.4; 92.2 -> 93.4. CIFAR100: 76.3 -> 76.7; 77.6 -> 78.0; 78.5 -> 79.1Improved
Add penal connection to ResNetResNet101 and ResNet152 · ImageNet-1K valaccuracy: 80.7 -> 81.1; 81.1 -> 81.4Improved

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