Rethinking the Role of Normalization and Residual Blocks for Spiking Neural Networks

Biologically inspired spiking neural networks (SNNs) are widely used to realize ultralow-power energy consumption. However, deep SNNs are not easy to train due to the excessive firing of spiking neurons in the hidden layers. To tackle this problem, we propose a novel but simple normalization techniq...

Descripción completa

Detalles Bibliográficos
Autores principales: Ikegawa, Shin-ichi, Saiin, Ryuji, Sawada, Yoshihide, Natori, Naotake
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9028401/
https://www.ncbi.nlm.nih.gov/pubmed/35458860
http://dx.doi.org/10.3390/s22082876

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9028401/
https://www.ncbi.nlm.nih.gov/pubmed/35458860
http://dx.doi.org/10.3390/s22082876

Ejemplares similares