Learning Equations from Chaos: Symbolic Recovery Despite 5x Signal Noise
bravo_abad · x · 2026-10-10
Can ML discover the equations of chaotic systems where trajectory fitting is unstable? Chesebro et al. tackle the training problem directly.
Their method combines known differential equations with a neural network learning the missing terms, stabilizes dynamics with prediction-error feedback during training, then applies symbolic regression to extract explicit equations.
On a chaotic electrical circuit, the method recovered the correct functional form even when one measurement had noise five times stronger than the signal; it was then applied to simulated neuron networks to derive reduced equations.
More from Research
- Domingos Cites New Result Claiming RL Is 'Basically Useless' vs Supervised Learning — pmddomingos · 2026-10-23
- Wolfram Opens Rule 30 Prizes to AIs: $30,000 for Three Open Problems — cephaloform · 2026-10-23
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23
- EMNLP paper: diffusion LMs internally encode latent denoising timestep representations — gsarti_ · 2026-10-23
- KU Leuven and VIB open two Group Leader professorships in AI for Biology, start 2027 — jpillowtime · 2026-10-23
- Subspace Tuning curbs LLM catastrophic forgetting by freezing principal singular directions — scottniekum · 2026-10-23