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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add meta-prediction-error objective (ablation) | Meta-PCN · CIFAR-10 VGG-13 | top-1 accuracy (%): 10.0 -> 89.5 | Improved |
| add variance-based weight regularization (ablation) | Meta-PCN · CIFAR-10 VGG-13 | accuracy (%): 1.3% improvement | Improved |
| replace conventional PCN with Meta-PCN | PCN · CIFAR-10 VGG-13 | top-1 accuracy (%): 12 -> 89.53 | Improved |
| replace backpropagation with Meta-PCN | BP · CIFAR-10 VGG-13 | top-1 accuracy (%): 87.85 -> 89.53 | Improved |
| replace backpropagation with Meta-PCN | BP · 30 configurations | accuracy (%): average improvement 2.15% | Improved |
| replace backpropagation with Meta-PCN | BP · CIFAR-100 ResNet-18 Top-1 | top-1 accuracy (%): BP leads by 0.02% | No clear effect |
Closest papers by meaning
- Benchmarking Predictive Coding Networks -- Made Simple (ICLR 2025 · similarity 0.89)
- $\mu$PC: Scaling Predictive Coding to 100+ Layer Networks (NeurIPS 2025 · similarity 0.89)
- Training a Predictive Coding Network on ImageNet using Equilibrium Propagation (NeurIPS 2026 · similarity 0.88)
- Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? (NeurIPS 2024 · similarity 0.87)
- A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks (ICLR 2024 · similarity 0.87)
- Understanding Sample Efficiency in Predictive Coding (NeurIPS 2026 · similarity 0.86)
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.
