Skip to main

Vocabulary of natural language processing

Search from vocabulary

Concept information

Término preferido

contrastive learning  

Definición

  • A self-supervised paradigm where a model is trained to learn useful representations of input data by contrasting similar and dissimilar samples. (Aswath et al., Segmentation in large-scale cellular electron microscopy with deep learning: A literature survey, in Medical Image Analysis, 2023)

Concepto genérico

Ejemplo

  • Contrastive learning has been extensively studied in sentence embedding learning which assumes that the embeddings of different views of the same sentence are closer. (Wu, Gao, Lin, Han, Wang & Hu, 2022)

En otras lenguas

URI

http://data.loterre.fr/ark:/67375/8LP-ZPN7F7DW-V

Descargue este concepto:

RDF/XML TURTLE JSON-LD última modificación 14/5/24