Cargando…
Bayesian continual learning via spiking neural networks
Among the main features of biological intelligence are energy efficiency, capacity for continual adaptation, and risk management via uncertainty quantification. Neuromorphic engineering has been thus far mostly driven by the goal of implementing energy-efficient machines that take inspiration from t...
Autores principales: | Skatchkovsky, Nicolas, Jang, Hyeryung, Simeone, Osvaldo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9708898/ https://www.ncbi.nlm.nih.gov/pubmed/36465962 http://dx.doi.org/10.3389/fncom.2022.1037976 |
Ejemplares similares
-
Accelerated Physical Emulation of Bayesian Inference in Spiking Neural Networks
por: Kungl, Akos F., et al.
Publicado: (2019) -
Stable learning of functional maps in self-organizing spiking neural networks with continuous synaptic plasticity
por: Srinivasa, Narayan, et al.
Publicado: (2013) -
Meta-SpikePropamine: learning to learn with synaptic plasticity in spiking neural networks
por: Schmidgall, Samuel, et al.
Publicado: (2023) -
Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks
por: Gardner, Brian, et al.
Publicado: (2021) -
Integration of Continuous-Time Dynamics in a Spiking Neural Network Simulator
por: Hahne, Jan, et al.
Publicado: (2017)