Back-Propagation Learning in Deep Spike-By-Spike Networks
Artificial neural networks (ANNs) are important building blocks in technical applications. They rely on noiseless continuous signals in stark contrast to the discrete action potentials stochastically exchanged among the neurons in real brains. We propose to bridge this gap with Spike-by-Spike (SbS)...
Main Authors: | David Rotermund, Klaus R. Pawelzik |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2019-08-01
|
Series: | Frontiers in Computational Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fncom.2019.00055/full |
Similar Items
-
Neuronal-Plasticity and Reward-Propagation Improved Recurrent Spiking Neural Networks
by: Shuncheng Jia, et al.
Published: (2021-03-01) -
Probabilistic Spike Propagation for Efficient Hardware Implementation of Spiking Neural Networks
by: Abinand Nallathambi, et al.
Published: (2021-07-01) -
A Synaptic Pruning-Based Spiking Neural Network for Hand-Written Digits Classification
by: Faramarz Faghihi, et al.
Published: (2022-02-01) -
Accelerating Spike-by-Spike Neural Networks on FPGA With Hybrid Custom Floating-Point and Logarithmic Dot-Product Approximation
by: Yarib Nevarez, et al.
Published: (2021-01-01) -
Toward a Lossless Conversion for Spiking Neural Networks with Negative‐Spike Dynamics
by: Chenglong Zou, et al.
Published: (2023-12-01)