Skip to main

Vocabulary of natural language processing (POC)

Search from vocabulary

Concept information

NLP methods and tools > model > representation model > hidden representation

Término preferido

hidden representation  

Definición

  • The abstract multidimensional space associated to each layer of a neural network where the representation of the learned data is implicitly built. Latent space contains the meaningful internal features representations of learned data, which makes it not directly interpretable. (Kaadoud et al., Explainable AI: a narrative review at the crossroad of Knowledge Discovery, Knowledge Representation and Representation Learning, 2021)

Concepto genérico

Etiquetas alternativas

  • hidden embedding
  • hidden state
  • latent representation
  • latent space

En otras lenguas

URI

http://data.loterre.fr/ark:/67375/8LP-W5408R37-4

Descargue este concepto:

RDF/XML TURTLE JSON-LD última modificación 27/6/24