A single recurrent network trained on masked sensory prediction and motion develops co-emergent grid and place cells that qualitatively match multiple experimental observations without any spatial supervision.
Global modules robustly emerge from local interactions and smooth gradients.Nature, 640(8057):155–164, April 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Joint training of NCA rules and SIREN pre-patterns improves robustness, encoding capacity, and symmetry breaking compared to purely self-organizing models by offloading information to initial conditions.
citing papers explorer
-
A simple model of co-emergence of grid and place fields
A single recurrent network trained on masked sensory prediction and motion develops co-emergent grid and place cells that qualitatively match multiple experimental observations without any spatial supervision.
-
Learning Developmental Scaffoldings to Guide Self-Organisation
Joint training of NCA rules and SIREN pre-patterns improves robustness, encoding capacity, and symmetry breaking compared to purely self-organizing models by offloading information to initial conditions.