Cargando…
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...
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: | |
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 |
Ejemplares similares
-
Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation
por: Scellier, Benjamin, et al.
Publicado: (2017) -
EqSpike: spike-driven equilibrium propagation for neuromorphic implementations
por: Martin, Erwann, et al.
Publicado: (2021) -
Incep-EEGNet: A ConvNet for Motor Imagery Decoding
por: Riyad, Mouad, et al.
Publicado: (2020) -
PCA driven mixed filter pruning for efficient convNets
por: Ahmed, Waqas, et al.
Publicado: (2022) -
Synaptic metaplasticity in binarized neural networks
por: Laborieux, Axel, et al.
Publicado: (2021)