Cargando...

TRACX2: a connectionist autoencoder using graded chunks to model infant visual statistical learning

Even newborn infants are able to extract structure from a stream of sensory inputs; yet how this is achieved remains largely a mystery. We present a connectionist autoencoder model, TRACX2, that learns to extract sequence structure by gradually constructing chunks, storing these chunks in a distribu...

Descrición completa

Gardado en:
Detalles Bibliográficos
Publicado en:Philos Trans R Soc Lond B Biol Sci
Main Authors: Mareschal, Denis, French, Robert M.
Formato: Artigo
Idioma:Inglês
Publicado: The Royal Society 2017
Assuntos:
Acceso en liña:https://ncbi.nlm.nih.gov/pmc/articles/PMC5124082/
https://ncbi.nlm.nih.gov/pubmed/27872375
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1098/rstb.2016.0057
Tags: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!