Emergence of grid-like representations by training recurrent neural networks to perform spatial localization

TL;DR

Training recurrent neural networks on spatial navigation tasks naturally produces grid-like and other spatially responsive units, providing insights into how such neural representations may emerge in biological systems.

Contribution

This study demonstrates that grid cells and related spatial responses can emerge in RNNs trained for navigation, offering a computational perspective on neural spatial coding.

Findings

Grid-like response patterns emerged in trained RNNs.

Units exhibiting border and band-like spatial responses also appeared.

Emergence of these patterns aligns with developmental observations in mammals.

Abstract

Decades of research on the neural code underlying spatial navigation have revealed a diverse set of neural response properties. The Entorhinal Cortex (EC) of the mammalian brain contains a rich set of spatial correlates, including grid cells which encode space using tessellating patterns. However, the mechanisms and functional significance of these spatial representations remain largely mysterious. As a new way to understand these neural representations, we trained recurrent neural networks (RNNs) to perform navigation tasks in 2D arenas based on velocity inputs. Surprisingly, we find that grid-like spatial response patterns emerge in trained networks, along with units that exhibit other spatial correlates, including border cells and band-like cells. All these different functional types of neurons have been observed experimentally. The order of the emergence of grid-like and border cells is also consistent with observations from developmental studies. Together, our results suggest that grid cells, border cells and others as observed in EC may be a natural solution for representing space efficiently given the predominant recurrent connections in the neural circuits.