Advertisement

Grid-like units help deep learning agent to navigate

Outlook

Summary

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.

Keywords

Navigation Spatial learning Modeling Artificial intelligence 

References

  1. Banino, A., Barry, C., Uria, B., Blundell, C., Lillicrap, T., Mirowski, P., … Kumaran, D. (2018). Vector-based navigation using grid-like representations in artificial agents. Nature, 557, 429–433. doi: https://doi.org/10.1038/s41586-018-0102-6 CrossRefPubMedGoogle Scholar
  2. Cheng, K., & Jeffery, K. J. (2017). Spatial cognition. In J. Call (Ed.), APA handbook of comparative psychology (Vol. 2, pp. 463–483). Washington, DC: American Psychological Association.Google Scholar
  3. Lambrinos, D., Möller, R., Labhart, T., Pfeifer, R., & Wehner, R. (2000). A mobile robot employing insect strategies for navigation. Robotics and Autonomous Systems, 30, 39–64.CrossRefGoogle Scholar
  4. Savelli, F., & Knierim, J. J. (2018). AI mimics brain codes for navigation. Nature, 557, 313–314.CrossRefPubMedGoogle Scholar
  5. Stone, T., Webb, B., Adden, A., Weddig, N. B., Honkanen, A., Templin, R., … Heinze, S. (2017). An anatomically constrained model for path integration in the bee brain. Current Biology, 27, 3069–3085.CrossRefPubMedGoogle Scholar

Copyright information

© Psychonomic Society, Inc. 2018

Authors and Affiliations

  1. 1.Department of Biological SciencesMacquarie UniversitySydneyAustralia

Personalised recommendations