Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures

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...

Full description

Bibliographic Details
Main Authors: Chankyu Lee, Syed Shakib Sarwar, Priyadarshini Panda, Gopalakrishnan Srinivasan, Kaushik Roy
Format: Article
Language:English
Published: Frontiers Media S.A. 2020-02-01
Series:Frontiers in Neuroscience
Subjects:
spiking neural network
convolutional neural network
spike-based learning rule
gradient descent backpropagation
leaky integrate and fire neuron
Online Access:https://www.frontiersin.org/article/10.3389/fnins.2020.00119/full

Internet

https://www.frontiersin.org/article/10.3389/fnins.2020.00119/full

Similar Items