AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Adaptive Coding Emerges in Stabilized Supralinear Networks Trained with Local Plasticity

Haoyu Albert Wang, Wei P Dai, Jialun Ma, Jiawei Zhang, jinqi liu, Mingchen Jiang, Mingqing Xiao, Yansen Wang, Dongqi Han, Dongsheng Li, Yuguo Yu

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Hebbian and predictive coding

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
Train SSN with local plasticity (BCM feedforward, CM recurrent) instead of hand-designed connectivitySSN · grating stimuli, V1-like tuningcontrast-dependent tuning sharpeningImproved
Use SSN representations instead of ICA, sparse coding, P-VAE, PredNet, PredCoding, SimCLRSSN (14,400 neurons) · CIFAR-10 classification, low contrastclassification accuracyImproved
Use SSN representations under increasing noiseSSN · CIFAR-10 classification, noiseclassification accuracyImproved
Use SSN versus PredNet under noise distortion on grating orientation classificationSSN · Gabor grating orientation classification, noiseaccuracyNo clear effect
Add E-to-E recurrent connections (ablation)SSN · low-contrast conditionstask performanceImproved
Add I-to-E recurrent connections (ablation)SSN · orientation and CIFAR-10 taskstask performance and stabilityImproved

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