Sequence architectures and attention · MLD-0908
Position embedding
A learned or fixed vector representation of a position.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Add absolute position vectors to token embeddings.
Original caveat
Learned absolute tables may limit straightforward extrapolation.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · NLP.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Attention Is All You Need ↗ · Consulted
- Transformers glossary ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗