AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Stable and Scalable Deep Predictive Coding Networks with Meta Prediction Errors

Myoung Hoon Ha, Hyunjun Kim, Yoondo Sung, Youngha Jo, Min S. Kang, Sang Wan Lee

ICLR 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
add meta-prediction-error objective (ablation)Meta-PCN · CIFAR-10 VGG-13top-1 accuracy (%): 10.0 -> 89.5Improved
add variance-based weight regularization (ablation)Meta-PCN · CIFAR-10 VGG-13accuracy (%): 1.3% improvementImproved
replace conventional PCN with Meta-PCNPCN · CIFAR-10 VGG-13top-1 accuracy (%): 12 -> 89.53Improved
replace backpropagation with Meta-PCNBP · CIFAR-10 VGG-13top-1 accuracy (%): 87.85 -> 89.53Improved
replace backpropagation with Meta-PCNBP · 30 configurationsaccuracy (%): average improvement 2.15%Improved
replace backpropagation with Meta-PCNBP · CIFAR-100 ResNet-18 Top-1top-1 accuracy (%): BP leads by 0.02%No clear effect

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