Toward Scalable, Efficient, and Accurate Deep Spiking Neural Networks With Backward Residual Connections, Stochastic Softmax, and Hybridization

Toward Scalable, Efficient, and Accurate Deep Spiking Neural Networks With Backward Residual Connections, Stochastic Softmax, and Hybridization

Spiking Neural Networks (SNNs) may offer an energy-efficient alternative for implementing deep learning applications. In recent years, there have been several proposals focused on supervised (conversion, spike-based gradient descent) and unsupervised (spike timing dependent plasticity) training meth...

Full description

Bibliographic Details
Main Authors: Priyadarshini Panda, Sai Aparna Aketi, Kaushik Roy
Format: Article
Language:English
Published: Frontiers Media S.A. 2020-06-01
Series:Frontiers in Neuroscience
Subjects:
spiking neural networks
energy-efficiency
backward residual connection
stochastic softmax
hybridization
improved accuracy
Online Access:https://www.frontiersin.org/article/10.3389/fnins.2020.00653/full

Internet

https://www.frontiersin.org/article/10.3389/fnins.2020.00653/full

Similar Items