AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Functional building blocks of neural networks: from network motifs to collective dynamics

Jian Zhang, Yue Sun, Wangzi Yao, Tielin Zhang

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired network comparison

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 Level-1 motif regularization to a recurrent networkRNN · PDMmean accuracy: 87.1 -> 91.9Improved
add Level-1 motif regularization to a recurrent networkRNN · TIDIGITSmean accuracy: 40.9 -> 45.0Improved
add Level-1 motif regularization to a recurrent networkRNN · Sequential MNISTmean accuracy: 61.7 -> 67.0Improved
use Level-1 motifs instead of Level-2 motifs (ablation)motif RNN · MNIST noise robustnessmean accuracy: 9.5±1.2%Improved
use Level-1 motifs instead of Level-3 motifs (ablation)motif RNN · PDMmean accuracy: 4.7±0.6%Improved
use Level-1 motifs instead of Level-3 motifs (ablation)motif RNN · TIDIGITSmean accuracy: 5.3±0.7%Improved
use Level-3 motifs instead of Level-1 motifs (ablation)motif RNN · Ant-v2 (2M steps)score: +384.5 ± 125.1Improved
use Level-3 motifs instead of Level-1 motifs (ablation)motif RNN · Ant-v2 (5M steps)score: +417.5 ± 164.3Improved
use Level-3 motifs instead of Level-1 motifs (ablation)motif RNN · InvertedPendulum-v2convergence speed: 31.8 ± 9.2% fasterImproved
add Level-3 motif regularization to a recurrent networkRNN · Ant-v2 (5M steps)score: 2882.1 -> 4258.0Improved
use motif regularization instead of LSTM (ablation)RNN · Sequential MNISTmean accuracy: 68.19 -> 67.0No clear effect
use very small relaxation beta (ablation)motif regularization · PDMaccuracyHurt

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