Grid-like units help deep learning agent to navigate

Ken Cheng

doi:10.3758/s13420-018-0329-y

Grid-like units help deep learning agent to navigate

Ken Cheng^*

^*Corresponding author for this work

Research output: Contribution to journal › Editorial › peer-review

1 Citation (Scopus)

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.

Original language	English
Pages (from-to)	3-4
Number of pages	2
Journal	Learning and Behavior
Volume	47
Issue number	1
DOIs	https://doi.org/10.3758/s13420-018-0329-y
Publication status	Published - Mar 2019

Keywords

Artificial intelligence
Modeling
Navigation
Spatial learning

Access to Document

10.3758/s13420-018-0329-y

Cite this

@article{caefbb0090a74b07808ef0c4ffb14ed3,

title = "Grid-like units help deep learning agent to navigate",

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.",

keywords = "Artificial intelligence, Modeling, Navigation, Spatial learning",

author = "Ken Cheng",

year = "2019",

month = mar,

doi = "10.3758/s13420-018-0329-y",

language = "English",

volume = "47",

pages = "3--4",

journal = "Learning and Behavior",

issn = "1543-4494",

publisher = "Springer, Springer Nature",

number = "1",

}

TY - JOUR

T1 - Grid-like units help deep learning agent to navigate

AU - Cheng, Ken

PY - 2019/3

Y1 - 2019/3

N2 - 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.

AB - 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.

KW - Artificial intelligence

KW - Modeling

KW - Navigation

KW - Spatial learning

UR - http://www.scopus.com/inward/record.url?scp=85048544661&partnerID=8YFLogxK

U2 - 10.3758/s13420-018-0329-y

DO - 10.3758/s13420-018-0329-y

M3 - Editorial

C2 - 29948880

AN - SCOPUS:85048544661

SN - 1543-4494

VL - 47

SP - 3

EP - 4

JO - Learning and Behavior

JF - Learning and Behavior

IS - 1

ER -

Grid-like units help deep learning agent to navigate

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this