Cargando...

Random synaptic feedback weights support error backpropagation for deep learning

The brain processes information through multiple layers of neurons. This deep architecture is representationally powerful, but complicates learning because it is difficult to identify the responsible neurons when a mistake is made. In machine learning, the backpropagation algorithm assigns blame by...

Descrición completa

Gardado en:
Detalles Bibliográficos
Publicado en:Nat Commun
Main Authors: Lillicrap, Timothy P., Cownden, Daniel, Tweed, Douglas B., Akerman, Colin J.
Formato: Artigo
Idioma:Inglês
Publicado: Nature Publishing Group 2016
Assuntos:
Acceso en liña:https://ncbi.nlm.nih.gov/pmc/articles/PMC5105169/
https://ncbi.nlm.nih.gov/pubmed/27824044
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1038/ncomms13276
Tags: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!