Cargando…
First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures
Spiking neural networks (SNNs) are well-suited to process asynchronous event-based data. Most of the existing SNNs use rate-coding schemes that focus on firing rate (FR), and so they generally ignore the spike timing in events. On the contrary, methods based on temporal coding, particularly time-to-...
Autores principales: | Liu, Siying, Leung, Vincent C. H., Dragotti, Pier Luigi |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10577212/ https://www.ncbi.nlm.nih.gov/pubmed/37849889 http://dx.doi.org/10.3389/fnins.2023.1266003 |
Ejemplares similares
-
Spiking Autoencoders With Temporal Coding
por: Comşa, Iulia-Maria, et al.
Publicado: (2021) -
Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators Using Time Compression Supporting Multiple Spike Codes
por: Xu, Changqing, et al.
Publicado: (2020) -
Training Spiking Neural Networks for Reinforcement Learning Tasks With Temporal Coding Method
por: Wu, Guanlin, et al.
Publicado: (2022) -
Efficient Processing of Spatio-Temporal Data Streams With Spiking Neural Networks
por: Kugele, Alexander, et al.
Publicado: (2020) -
Efficient human activity recognition with spatio-temporal spiking neural networks
por: Li, Yuhang, et al.
Publicado: (2023)