Research map / Time series / Causal and generative time series
On the difficulty of learning chaotic dynamics with RNNs
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 |
|---|---|---|---|
| use sparsely forced BPTT with learning interval near predictability time instead of classical BPTT with gradient clipping | PLRNN, vanilla RNN, LSTM · Lorenz and Duffing reconstruction | D_stsp / D_H | Helped |
| reset chunk initial condition to zero or last forward-iterated state instead of control value (ablation) | sparsely forced BPTT · Lorenz | D_stsp / D_H | Hurt |
| use learning interval tau matching ln2/lambda_max rather than too small or too large (ablation) | sparsely forced BPTT · Lorenz, Duffing, weather | D_stsp / D_H | Helped |
Closest papers by meaning
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.90)
- Learning Dynamics of RNNs in Closed-Loop Environments (NeurIPS 2025 · similarity 0.89)
- Learning dynamics in linear recurrent neural networks (ICML 2025 · similarity 0.89)
- Mechanistic Interpretability of RNNs emulating Hidden Markov Models (NeurIPS 2025 · similarity 0.88)
- When are dynamical systems learned from time series data statistically accurate? (NeurIPS 2024 · similarity 0.88)
- Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction (NeurIPS 2024 · similarity 0.88)
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.