Research map / Probabilistic and scientific modeling / Dynamical systems
Emergence of grid-like representations by training recurrent neural networks to perform spatial localization
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 |
|---|---|---|---|
| Train a recurrent network to estimate location from velocity inputs with noise and metabolic-cost regularization | RNN · 2D navigation in square, triangular, and hexagonal arenas | grid-like responses | Helped |
| Train a recurrent network to estimate location from velocity inputs | RNN · 2D navigation in square, triangular, and hexagonal arenas | spatial response types | Helped |
| Use boundary interactions as a localization cue | Trained RNN · 2D navigation | localization error | Helped |
| Add metabolic-cost regularization (ablation) | RNN · 2D navigation | grid-like responses | Helped |
| Add network noise during training (ablation) | RNN · 2D navigation | grid-like responses | Helped |
Closest papers by meaning
- A simple model of co-emergence of grid and place fields (NeurIPS 2026 · similarity 0.91)
- Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems (NeurIPS 2024 · similarity 0.89)
- Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals (NeurIPS 2024 · similarity 0.89)
- REMI: Reconstructing Episodic Memory During Internally Driven Path Planning (NeurIPS 2025 · similarity 0.88)
- Not so griddy: Internal representations of RNNs path integrating more than one agent (NeurIPS 2024 · similarity 0.88)
- Learning Place Cell Representations and Context-Dependent Remapping (NeurIPS 2024 · similarity 0.87)
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.