Extracting grid cell characteristics from place cell inputs using non-negative principal component analysis (Dordek et al., 2016)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Emergence of grid-like representations by training recurrent neural networks to perform spatial localization (Cueva & Wei, 2018)concept0.742
  RNN model recapitulating grid cells; related work category 4.
• A unified theory for the origin of grid cells through the lens of pattern formation (Sorscher et al., 2019)concept0.742
  RNN model producing grid cells; cited as prior work recapitulating spatial representations.
• A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex (Hawkins et al., 2019)concept0.734
  Related work discussing grid cells in neocortex; mentioned as exploring similar ideas about cortical transformer-like computation.
• Novel place cell metric (largest connected component firing mass ratio) successfully distinguishes TEM-t memory neurons (place cells) from RNN neurons (grid cells)finding0.727
  Methodological validation result confirming the place-cell metric separates cell types in TEM-t.
• Vector-based navigation using grid-like representations in artificial agents (Banino et al., 2018)concept0.727
  Demonstrated grid cell emergence in RNNs trained on spatial navigation; related work category 4.
• Making information explicit—extracting normal forms from computation.claim0.717
• Representing non-linearly separable functions requires a network with multiple layers.claim0.716
  Architectural requirement from machine learning.
• TEM-t with linear activations learns grid-cell-like position encoding representations in 2D spatial environmentsfinding0.716
  Empirical result showing TEM-t recapitulates entorhinal grid cell representations with linear post-transition activation.