method
active
method:sensory-landmark-position-encoding-stabilizationSensory Landmark Position Encoding Stabilization
Method for stabilising drifting recurrent position encodings by querying stored landmark memories to correct path-integrated position.
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- TEM-Transformer (TEM-t)implementsThe transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.
Methods (1)
method
- Key modification to transformers proposed in this paper: position encodings generated by a recurrent network trained on action sequences.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Mechanism for encoding sequence order in transformers; paper argues these should reflect learned structural representations rather than fixed sines/cosines.
- Gradient that tells a cell its correct position; stress arises from deviation from this gradient.
- Novel interpretive claim about position encodings inspired by the TEM-transformer correspondence.
- Forward-looking interpretive claim about the implications of recurrent position encodings for NLP research.
- Hypothesis that in language tasks, the abstract structure encoded in positional encodings corresponds to grammatical structure.
- what is the analogue of spatial positional encodings for higher order tasks such as language?question0.726Open question raised in Discussion about extending TEM-t principles beyond spatial navigation.
- Chinn et al. showed that tactile target experience promotes earlier mirror self-recognition in infants; noted as a future extension
- Input from environment that the agent models and predicts.