Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures

Spiking Neural Networks (SNNs) have recently emerged as a prominent neural computing paradigm. However, the typical shallow SNN architectures have limited capacity for expressing complex representations while training deep SNNs using input spikes has not been successful so far. Diverse methods have...

Descrición completa

Gardado en:
Detalles Bibliográficos
Main Authors: Chankyu Lee, Syed Shakib Sarwar, Priyadarshini Panda, Gopalakrishnan Srinivasan, Kaushik Roy
Formato: Artigo
Idioma:Inglês
Publicado: Frontiers Media S.A. 2020-02-01
Series:Frontiers in Neuroscience
Assuntos:
spiking neural network
convolutional neural network
spike-based learning rule
gradient descent backpropagation
leaky integrate and fire neuron
Acceso en liña:https://www.frontiersin.org/article/10.3389/fnins.2020.00119/full
Tags: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!

Títulos similares