Hopfield network can store multiple patterns, recall them via content-addressable memory, and generalise to novel patterns with the same underlying structure.

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

• Hopfield Networks is All You Need (Ramsauer et al., 2020)concept0.797
  Paper showing Hopfield networks are closely related to transformers; key intermediary result used to connect TEM to transformers.
• Storing infinite numbers of patterns in a spin-glass model of neural networks (Amit et al., 1985)concept0.774
  Result that original Hopfield network memory capacity scales linearly with network dimensionality; background for scaling discussion.
• Bioelectric pattern memories store target morphology for anatomical homeostasis.claim0.772
  Planarian head number can be permanently altered by re-writing bioelectric prepatterns.
• Patterns capture knowledge beyond the individual.claim0.770
  Why technologists love Alexander; patterns as mechanism for sharing and reusing design knowledge.
• Dense Associative Memory for Pattern Recognition (Krotov & Hopfield, 2016)concept0.764
  Paper exploring two-type feature binding in dense associative memory; analogous to TEM-t binding g and x in memory neurons.
• Deep representations have a special significance in recurrent networks, allowing coordinated behaviour without losing sensitivity to new inputs.claim0.759
  Importance of hierarchical structure for flexible coordination.
• The Internet is a communal memory that makes it possible for good sequences to be exchanged and spread rapidly.claim0.758
  Identifies the Internet as the natural location and accelerator for the gene pool of morphogenetic sequences.
• Planarian pattern memory is encoded in bioelectric attractor states within gap-junction-coupled networks, which can be re-written by channel modulation.hypothesis0.757
  Testable by computational modeling and experimental perturbation of specific bioelectric circuits.