Weight statistics controls dynamics in recurrent neural networks

Recurrent neural networks are complex non-linear systems, capable of ongoing activity in the absence of driving inputs. The dynamical properties of these systems, in particular their long-time attractor states, are determined on the microscopic level by the connection strengths w(ij) between the ind...

Descripción completa

Detalles Bibliográficos
Autores principales: Krauss, Patrick, Schuster, Marc, Dietrich, Verena, Schilling, Achim, Schulze, Holger, Metzner, Claus
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2019
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6456246/
https://www.ncbi.nlm.nih.gov/pubmed/30964879
http://dx.doi.org/10.1371/journal.pone.0214541

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6456246/
https://www.ncbi.nlm.nih.gov/pubmed/30964879
http://dx.doi.org/10.1371/journal.pone.0214541

Ejemplares similares