Research map / Architectures and efficiency / RNNs and normalization
Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 local recurrent predictive-coding processing to Plain-D | CIFAR-10 classification · CIFAR-10 test | error rate (%): 5.61 -> 4.89 | Helped |
| Add local recurrent predictive-coding processing to Plain-D | CIFAR-100 classification · CIFAR-100 test | error rate (%): 25.31 -> 21.77 | Helped |
| Add local recurrent predictive-coding processing to Plain-B | SVHN classification · SVHN test | error rate (%): 2.43 -> 1.96 | Helped |
| Add local recurrent predictive-coding processing to Plain-E | ImageNet classification · ImageNet validation, single-crop | top-1 error (%): 31.15 -> 25.31 | Helped |
| Increase recurrent cycles from 1 to 5 (ablation) | PCN-C · CIFAR-10 test | error rate (%): 5.70 -> 5.10 | Helped |
| Increase recurrent cycles from 1 to 5 (ablation) | PCN-C · CIFAR-100 test | error rate (%): 24.01 -> 22.43 | Helped |
| Increase recurrent cycles from 1 to 5 (ablation) | PCN-A · SVHN test | error rate (%): 2.29 -> 2.07 | Helped |
| Increase recurrent cycles from 1 to 5 (ablation) | PCN-B · SVHN test | error rate (%): 1.99 -> 1.96 | Helped |
| Use local rather than global recurrent processing | PCN · CIFAR-100 test | error rate (%): 27.42 -> 21.77 | Helped |
| Add more recurrent cycles (ablation) | PCN-E · ImageNet validation | top-1 error (%): 25.36 -> 25.31 | Helped |
Closest papers by meaning
- Benchmarking Predictive Coding Networks -- Made Simple (ICLR 2025 · similarity 0.89)
- A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks (ICLR 2024 · similarity 0.89)
- Training a Predictive Coding Network on ImageNet using Equilibrium Propagation (NeurIPS 2026 · similarity 0.88)
- $\mu$PC: Scaling Predictive Coding to 100+ Layer Networks (NeurIPS 2025 · similarity 0.88)
- Auto-Compressing Networks (NeurIPS 2025 · similarity 0.86)
- 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.