Cargando…
Brain-inspired replay for continual learning with artificial neural networks
Artificial neural networks suffer from catastrophic forgetting. Unlike humans, when these networks are trained on something new, they rapidly forget what was learned before. In the brain, a mechanism thought to be important for protecting memories is the reactivation of neuronal activity patterns re...
Autores principales: | van de Ven, Gido M., Siegelmann, Hava T., Tolias, Andreas S. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7426273/ https://www.ncbi.nlm.nih.gov/pubmed/32792531 http://dx.doi.org/10.1038/s41467-020-17866-2 |
Ejemplares similares
-
Biologically inspired load balancing mechanism in neocortical competitive learning
por: Tal, Amir, et al.
Publicado: (2014) -
Three types of incremental learning
por: van de Ven, Gido M., et al.
Publicado: (2022) -
Sleep-like unsupervised replay reduces catastrophic forgetting in artificial neural networks
por: Tadros, Timothy, et al.
Publicado: (2022) -
Neural Avalanches at the Critical Point between Replay and Non-Replay of Spatiotemporal Patterns
por: Scarpetta, Silvia, et al.
Publicado: (2013) -
Complex Systems Science and Brain Dynamics
por: Siegelmann, Hava T.
Publicado: (2010)