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

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.

References in corpus (5)

• Pixel Recurrent Neural Networks
• DRAW: A Recurrent Neural Network For Image Generation
• Accurate path integration in continuous attractor network models of grid cells
• The Sense of Place: Grid Cells in the Brain and the Transcendental Number e
• Generative Image Modeling Using Spatial LSTMs

Cited by in corpus (26)

• Artificial neural networks for neuroscientists: A primer
• Learning to Navigate in Cities Without a Map
• Will we ever have Conscious Machines?
• Universality and individuality in neural dynamics across large populations of recurrent networks
• Cognitive swarming in complex environments with attractor dynamics and oscillatory computing
• Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networks
• Learning models for visual 3D localization with implicit mapping
• Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells
• How recurrent networks implement contextual processing in sentiment analysis
• SpikePropamine: Differentiable Plasticity in Spiking Neural Networks
• Deep neuroethology of a virtual rodent
• Learning to Predict Without Looking Ahead: World Models Without Forward Prediction
• If deep learning is the answer, then what is the question?
• MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic Navigation
• Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
• Grid Cells Are Ubiquitous in Neural Networks
• On Path Integration of Grid Cells: Group Representation and Isotropic Scaling
• Cross-View Policy Learning for Street Navigation
• Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction
• Semi-supervised Sequential Generative Models
• The Roles of Supervised Machine Learning in Systems Neuroscience
• Imitation Learning of Factored Multi-agent Reactive Models
• LOOPER: Inferring computational algorithms enacted by neuronal population dynamics
• Hippocampal representations emerge when training recurrent neural networks on a memory dependent maze navigation task
• Is coding a relevant metaphor for building AI? A commentary on "Is coding a relevant metaphor for the brain?", by Romain Brette
• Implementing Inductive bias for different navigation tasks through diverse RNN attractors