Research map / Architectures and efficiency / RNNs and normalization
Predictive coding in balanced neural networks with noise, chaos and delays
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 |
|---|---|---|---|
| Increase balance without delays | Balanced predictive coding · No delays; stochastic noise | decoder variance: power law suppression of variance with exponent -1 for noise | Helped |
| Increase balance without delays | Balanced predictive coding · No delays; weight-disorder-induced chaos | decoder variance: power law suppression of variance with exponent -2 for chaos | Helped |
| Increase balance | Balanced predictive coding · No delays; stochastic noise | decoder error scaling with network size: O(1/b\sqrt N) | Helped |
| Add synaptic delay | Balanced predictive coding · Noise and delays | decoder variance | Mixed |
| Set balance to half the maximal stable feedback | Balanced predictive coding · Noise and delays | decoder variance: tilde b_opt=\frac{1}{2}\tilde b_c | Helped |
| Increase delay | Balanced predictive coding · Noise and delays | optimal decoder error: exponent 1/2 for noise | Hurt |
| Increase delay | Balanced predictive coding · Chaos and delays | optimal decoder error: exponent 1 for chaos | Hurt |
| Increase balance beyond the delay-dependent stability limit | Balanced predictive coding · Noise and delays | stability | Hurt |
| Increase delay | Balanced predictive coding · Noise and delays | maximal stable negative feedback | Hurt |
| Add noise | Balanced predictive coding · With delays | critical balance before oscillatory instability | Helped |
| Operate near the maximal stable balance | Balanced predictive coding · Chaos and small delays | decoder variance | Helped |
Closest papers by meaning
- Improving Deep Learning Speed and Performance Through Synaptic Neural Balance (AAAI 2025 · similarity 0.88)
- Unconditional stability of a recurrent neural circuit implementing divisive normalization (NeurIPS 2024 · similarity 0.87)
- Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons (NeurIPS 2026 · similarity 0.86)
- A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks (ICLR 2024 · similarity 0.86)
- Feedback control guides credit assignment in recurrent neural networks (NeurIPS 2024 · similarity 0.86)
- Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks (NeurIPS 2025 · 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.