Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias

Equilibrium Propagation is a biologically-inspired algorithm that trains convergent recurrent neural networks with a local learning rule. This approach constitutes a major lead to allow learning-capable neuromophic systems and comes with strong theoretical guarantees. Equilibrium propagation operate...

Descripción completa

Detalles Bibliográficos
Autores principales: Laborieux, Axel, Ernoult, Maxence, Scellier, Benjamin, Bengio, Yoshua, Grollier, Julie, Querlioz, Damien
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7930909/
https://www.ncbi.nlm.nih.gov/pubmed/33679315
http://dx.doi.org/10.3389/fnins.2021.633674

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7930909/
https://www.ncbi.nlm.nih.gov/pubmed/33679315
http://dx.doi.org/10.3389/fnins.2021.633674

Ejemplares similares