Efficient Inference in Structured Spaces
Author(s) -
Honi Sanders,
Matthew A. Wilson,
Mirko Klukas,
Sugandha Sharma,
Ila Fiete
Publication year - 2020
Publication title -
cell
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 26.304
H-Index - 776
eISSN - 1097-4172
pISSN - 0092-8674
DOI - 10.1016/j.cell.2020.11.008
Subject(s) - cognitive map , context (archaeology) , entorhinal cortex , grid cell , inference , representation (politics) , artificial intelligence , computer science , hippocampus , cognitive science , biology , spatial cognition , cognition , grid , neuroscience , psychology , mathematics , paleontology , geometry , politics , political science , law
Whittington et al. demonstrate how network architectures defined in a spatial context may be useful for inference on different types of relational knowledge. These architectures allow for learning the structure of the environment and then transferring that knowledge to allow prediction of novel transitions.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom