Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

Spiking neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into ac...

Descripción completa

Detalles Bibliográficos
Autores principales: Rueckauer, Bodo, Lungu, Iulia-Alexandra, Hu, Yuhuang, Pfeiffer, Michael, Liu, Shih-Chii
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2017
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5770641/
https://www.ncbi.nlm.nih.gov/pubmed/29375284
http://dx.doi.org/10.3389/fnins.2017.00682

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5770641/
https://www.ncbi.nlm.nih.gov/pubmed/29375284
http://dx.doi.org/10.3389/fnins.2017.00682

Ejemplares similares