method
active
method:recurrent-position-encodings

Recurrent Position Encodings

Key modification to transformers proposed in this paper: position encodings generated by a recurrent network trained on action sequences.

Neighborhood — ranked by edge-count

Frameworks (1)

framework
  • The transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.

Concepts (2)

concept
  • Path Integration
    analogous_to
    Neural mechanism for tracking location through accumulation of self-movement vectors; shown to play the role of position encodings in TEM.
  • Mechanism for encoding sequence order in transformers; paper argues these should reflect learned structural representations rather than fixed sines/cosines.

Methods (1)

method

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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