Concept information
Término preferido
label smoothing
Definición
- A technique used in neural networks for tasks like image classification and speech recognition to prevent model overfitting and improve its generalization ability by distributing probability mass to all labels, not just the gold label.
Concepto genérico
Ejemplo
- During the training process the value of label smoothing is set to 0.1 and dropout is set to 0.1. (Cheng, Yao, Xin, An, Li, Li & Zou, 2024)
En otras lenguas
-
francés
URI
http://data.loterre.fr/ark:/67375/8LP-S7V1DRMJ-9
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}