Grid-like units help deep learning agent to navigate.

Journal: Learning & behavior
PMID:

Abstract

An artificial-intelligence model based on deep learning developed units in a hidden layer that resembled mammalian grid cells in the hippocampus when the agent was taught to integrate paths. The full model performed sophisticated navigational tasks-in some cases even better than a human.

Authors

  • Ken Cheng
    Department of Biological Sciences, Macquarie University, Sydney, NSW, 2109, Australia. ken.cheng@mq.edu.au.