TEM-t learns grid cells in hexagonal 6-connected worlds

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

• TEM-t with linear activations learns grid-cell-like position encoding representations in 2D spatial environmentsfinding0.845
  Empirical result showing TEM-t recapitulates entorhinal grid cell representations with linear post-transition activation.
• TEM-t learns band-cell-like position encoding representations resembling Krupic et al. band cellsfinding0.793
  Empirical result showing TEM-t position encodings also recapitulate band cells, not just grid cells.
• TEM-t memory neurons show spatially-tuned firing resembling hippocampal place cells in each environmentfinding0.774
  Empirical result demonstrating that the sparse softmax activation of memory neurons produces place-cell-like spatial tuning.
• TEM-t instantiates hippocampal indexing theory by using memory neurons to bind cortical representations across brain regionsclaim0.752
  Theoretical claim linking the TEM-t architecture to the Teyler-Rudy hippocampal indexing theory.
• TEM-t requires less time per gradient step than TEMfinding0.737
  Empirical computational efficiency result comparing TEM-t to the original TEM implementation.
• 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.
• TEM-Transformer (TEM-t)framework0.723
  The transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.
• Emergence of grid-like representations by training recurrent neural networks to perform spatial localization (Cueva & Wei, 2018)concept0.705
  RNN model recapitulating grid cells; related work category 4.