Grid-like units help deep learning agent to navigate

Ken Cheng*

*Corresponding author for this work

Research output: Contribution to journalEditorialpeer-review


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.

Original languageEnglish
Pages (from-to)3-4
Number of pages2
JournalLearning and Behavior
Issue number1
Publication statusPublished - Mar 2019


  • Artificial intelligence
  • Modeling
  • Navigation
  • Spatial learning


Dive into the research topics of 'Grid-like units help deep learning agent to navigate'. Together they form a unique fingerprint.

Cite this