Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this...
Main Authors: | Abhronil Sengupta, Yuting Ye, Robert Wang, Chiao Liu, Kaushik Roy |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2019-03-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2019.00095/full |
Similar Items
-
Exploring the Connection Between Binary and Spiking Neural Networks
by: Sen Lu, et al.
Published: (2020-06-01) -
Efficient Spike-Driven Learning With Dendritic Event-Based Processing
by: Shuangming Yang, et al.
Published: (2021-02-01) -
Always-On Sub-Microwatt Spiking Neural Network Based on Spike-Driven Clock- and Power-Gating for an Ultra-Low-Power Intelligent Device
by: Pavan Kumar Chundi, et al.
Published: (2021-07-01) -
Training Deep Spiking Neural Networks using Backpropagation
by: Jun Haeng Lee, et al.
Published: (2016-11-01) -
Efficient Spiking Neural Networks With Logarithmic Temporal Coding
by: Ming Zhang, et al.
Published: (2020-01-01)