Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals

Humans can learn several tasks in succession with minimal mutual interference but perform more poorly when trained on multiple tasks at once. The opposite is true for standard deep neural networks. Here, we propose novel computational constraints for artificial neural networks, inspired by earlier w...

Descripción completa

Detalles Bibliográficos
Autores principales: Flesch, Timo, Nagy, David G., Saxe, Andrew, Summerfield, Christopher
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9851563/
https://www.ncbi.nlm.nih.gov/pubmed/36656823
http://dx.doi.org/10.1371/journal.pcbi.1010808

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9851563/
https://www.ncbi.nlm.nih.gov/pubmed/36656823
http://dx.doi.org/10.1371/journal.pcbi.1010808

Ejemplares similares