Emergence of grid-like representations by training recurrent neural networks to perform spatial localization (Cueva & Wei, 2018)

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

• Vector-based navigation using grid-like representations in artificial agents (Banino et al., 2018)concept0.808
  Demonstrated grid cell emergence in RNNs trained on spatial navigation; related work category 4.
• Neural Representations of Location Composed of Spatially Periodic Bands (Krupic et al., 2012)concept0.794
  Discovery of band cells; TEM-t also recapitulates these representations.
• TEM-t with linear activations learns grid-cell-like position encoding representations in 2D spatial environmentsfinding0.780
  Empirical result showing TEM-t recapitulates entorhinal grid cell representations with linear post-transition activation.
• Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.780
  The paper's central thesis statement, presented prominently after the abstract
• Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.777
  Central hypothesis tested via manifold steering experiments across language models and video world models.
• The geometry of internal representations and the geometry of model behavior share a precise correspondence — representation geometry is a window into the inner world of neural networks.claim0.770
  The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.
• Olah et al. (2020) found that automatically trained computer vision models, regardless of architecture and training procedure, all arrive at similar functional structures organizing similar features into similar compositional hierarchies, closely resembling the primate visual cortex.finding0.767
  Empirical finding supporting the Universality Hypothesis; extended by the paper to consciousness
• would place-like representations emerge in memory neurons for activation functions other than softmax?question0.766
  Open empirical question left for future work about robustness of place cell emergence.