Concept information
Preferred term
self-attention layer
Definition
- A layer in the architecture of transformer-based models that allows the model to focus on different parts of the input sequence when processing each token to capture contextual relationships and dependencies within the input sequence.
Broader concept
In other languages
-
French
URI
http://data.loterre.fr/ark:/67375/8LP-DMDVS16W-4
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}