Cargando…
Synaptic metaplasticity in binarized neural networks
While deep neural networks have surpassed human performance in multiple situations, they are prone to catastrophic forgetting: upon training a new task, they rapidly forget previously learned ones. Neuroscience studies, based on idealized tasks, suggest that in the brain, synapses overcome this issu...
Autores principales: | Laborieux, Axel, Ernoult, Maxence, Hirtzlin, Tifenn, Querlioz, Damien |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8100137/ https://www.ncbi.nlm.nih.gov/pubmed/33953183 http://dx.doi.org/10.1038/s41467-021-22768-y |
Ejemplares similares
-
Digital Biologically Plausible Implementation of Binarized Neural Networks With Differential Hafnium Oxide Resistive Memory Arrays
por: Hirtzlin, Tifenn, et al.
Publicado: (2020) -
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias
por: Laborieux, Axel, et al.
Publicado: (2021) -
Neural-like computing with populations of superparamagnetic basis functions
por: Mizrahi, Alice, et al.
Publicado: (2018) -
Using Memristors for Robust Local Learning of Hardware Restricted Boltzmann Machines
por: Ernoult, Maxence, et al.
Publicado: (2019) -
Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification
por: Kim, Sungho, et al.
Publicado: (2019)