Cargando…
EXODUS: Stable and efficient training of spiking neural networks
INTRODUCTION: Spiking Neural Networks (SNNs) are gaining significant traction in machine learning tasks where energy-efficiency is of utmost importance. Training such networks using the state-of-the-art back-propagation through time (BPTT) is, however, very time-consuming. Previous work employs an e...
Autores principales: | Bauer, Felix C., Lenz, Gregor, Haghighatshoar, Saeid, Sheik, Sadique |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9945199/ https://www.ncbi.nlm.nih.gov/pubmed/36845419 http://dx.doi.org/10.3389/fnins.2023.1110444 |
Ejemplares similares
-
Adversarial attacks on spiking convolutional neural networks for event-based vision
por: Büchel, Julian, et al.
Publicado: (2022) -
Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications
por: Sorbaro, Martino, et al.
Publicado: (2020) -
SSTDP: Supervised Spike Timing Dependent Plasticity for Efficient Spiking Neural Network Training
por: Liu, Fangxin, et al.
Publicado: (2021) -
Memory-Efficient Synaptic Connectivity for Spike-Timing- Dependent Plasticity
por: Pedroni, Bruno U., et al.
Publicado: (2019) -
Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks
por: Mostafa, Hesham, et al.
Publicado: (2017)