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

03/21/2018
by   Christopher J. Cueva, et al.
0

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.

READ FULL TEXT

page 2

page 4

page 7

page 8

page 14

page 16

page 17

research
03/07/2020

Grid Cells Are Ubiquitous in Neural Networks

Grid cells are believed to play an important role in both spatial and no...
research
02/17/2021

Grid Cell Path Integration For Movement-Based Visual Object Recognition

Grid cells enable the brain to model the physical space of the world and...
research
02/18/2019

A computational model for grid maps in neural populations

Grid cells in the entorhinal cortex, together with place, speed and bord...
research
12/01/2022

A Topological Deep Learning Framework for Neural Spike Decoding

The brain's spatial orientation system uses different neuron ensembles t...
research
10/12/2018

Learning Grid-like Units with Vector Representation of Self-Position and Matrix Representation of Self-Motion

This paper proposes a model for learning grid-like units for spatial awa...
research
05/23/2018

Generalisation of structural knowledge in the Hippocampal-Entorhinal system

A central problem to understanding intelligence is the concept of genera...
research
05/20/2022

Emergence of Double-slit Interference by Representing Visual Space in Artificial Neural Networks

Artificial neural networks have realized incredible successes at image r...

Please sign up or login with your details

Forgot password? Click here to reset