Training Deep Spiking Neural Networks Using Backpropagation

Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Jun Haeng, Delbruck, Tobi, Pfeiffer, Michael
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2016
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5099523/
https://www.ncbi.nlm.nih.gov/pubmed/27877107
http://dx.doi.org/10.3389/fnins.2016.00508

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5099523/
https://www.ncbi.nlm.nih.gov/pubmed/27877107
http://dx.doi.org/10.3389/fnins.2016.00508

Ejemplares similares