Attention Layer
Layer AIO:AttentionLayer NOT_REVIEWED
A layer that implements dot-product attention also known as Luong-style attention.
Ontology IRI:
https://w3id.org/aio/AttentionLayer
Ontology Structure & Relationships
Parent Classes
Branches
Annotations & Sources
Definition Sources:
Subsets:
https://w3id.org/aio/LayerSubset
Curated AIMech Concepts Grounded to this Class
4 Concepts| Curated Concept | Kind | Mapping Relation | Rationale |
|---|---|---|---|
End-to-End Memory Network
AIMech:EndToEndMemoryNetwork |
Architectures | related_match | The architecture uses dot-product soft-attention reads, a component-level relation to the pinned attention-layer concept. This does not identify the whole model with one software layer or claim a verified API implementation. |
FlashAttention
AIMech:FlashAttention |
Algorithms | related_match | FlashAttention changes how attention is computed and stored, while this AIO target denotes a layer implementing attention. |
Key-Value Memory Network
AIMech:KeyValueMemoryNetwork |
Architectures | related_match | Key addressing uses dot-product soft attention. This relates one component to the pinned layer concept without equating the complete architecture with a software layer or asserting an inspected API implementation. |
Non-local block
AIMech:NonLocalBlock |
Layers & Modules | related_match | The embedded-Gaussian instance computes a softmax of pairwise embedded dot products and is directly related to the pinned dot-product attention layer. The native record also covers non-softmax functions and a residual wrapper, so the relationship is not family-wide equivalence or a forced subclass. |
Import Provenance & Upstream Synchronization
Source Repo: AIO GitHub
Release Version:
aio.jsonCommit:
397851c547…License: CC-BY-4.0
Imported At: 2026-10-10T07:34:10Z
SHA256:
8f741d71408c…
Source File:
data/aio/AttentionLayer.yaml