Research map / Probabilistic and scientific modeling / Dynamical systems
Charting and Navigating the Space of Solutions for Recurrent Neural Networks
Elia Turner, Kabir Vinay Dabholkar, Omri Barak
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 |
|---|---|---|---|
| use LSTM or GRU instead of vanilla RNN (ablation) | interval reproduction RNNs · Interval reproduction | distribution of solution types | Mixed |
| vary only random initialization with identical hyperparameters | vanilla RNNs (400 per task) · Delayed discrimination, Interval discrimination, Interval reproduction | diversity of dynamical solutions | Mixed |
| switch to context-dependent integration task | trained RNNs · Context-dependent integration | qualitative solution variability | No clear effect |
Closest papers by meaning
- Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks (NeurIPS 2025 · similarity 0.91)
- Learning dynamics in linear recurrent neural networks (ICML 2025 · similarity 0.90)
- Learning Dynamics of RNNs in Closed-Loop Environments (NeurIPS 2025 · similarity 0.88)
- Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks (ICLR 2024 · similarity 0.88)
- Feedback control guides credit assignment in recurrent neural networks (NeurIPS 2024 · similarity 0.88)
- Dynamical phases of short-term memory mechanisms in RNNs (ICML 2025 · 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.
