Synthesizing Images From Spatio-Temporal Representations Using Spike-Based Backpropagation
Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic applications require processing and extracting meaningful information from spatio-temporal data, represented as series o...
Main Authors: | Deboleena Roy, Priyadarshini Panda, Kaushik Roy |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2019-06-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2019.00621/full |
Similar Items
-
Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
by: Jacques Kaiser, et al.
Published: (2020-05-01) -
Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures
by: Chankyu Lee, et al.
Published: (2020-02-01) -
SpiLinC: Spiking Liquid-Ensemble Computing for Unsupervised Speech and Image Recognition
by: Gopalakrishnan Srinivasan, et al.
Published: (2018-08-01) -
Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks
by: Yujie Wu, et al.
Published: (2018-05-01) -
Feature Representations for Neuromorphic Audio Spike Streams
by: Jithendar Anumula, et al.
Published: (2018-02-01)