Concept information
Término preferido
transformer layer
Definición
- A module found in a transformer that computes self-attention over a sequence followed by an elementwise transformation of the output vectors. (Based on Merrill and Sabharwal, The Parallelism Tradeoff: Limitations of Log-Precision Transformers, in Transactions of the Association for Computational Linguistics, 2023)
Concepto genérico
En otras lenguas
-
francés
URI
http://data.loterre.fr/ark:/67375/8LP-DMWDBJ9Z-N
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}