Skip to content

Self-Attention

Definition
AI-generated

Self-attention computes pairwise interactions among positions in a single sequence (or set) so each position’s representation blends information from others via learned weights; stacked layers build transformer blocks when combined with position encodings and feedforward sublayers.

Topics
LLM and Agents
Related
Attention Mechanism Genome-Wide Association Study (GWAS) Large Language Model (LLM)

Why it matters in GWAS

Self-attention is the workhorse of DNA, RNA, and protein language models used for annotation and scoring; attention maps are descriptive but not guaranteed biological mechanisms without experiments.

Example usage

"Downstream interpretation uses Self-Attention to connect statistical evidence with biological context."

Attention Mechanism Genome-Wide Association Study (GWAS) Large Language Model (LLM) Masked Attention Multi-Head Attention Positional Encoding Transformer
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Vaswani A, et al. (2017). Attention is all you need. NeurIPS.
← Selection Pressure Sense strand →

Last updated (UTC · Git history)