Rethinking the Role of Normalization and Residual Blocks for Spiking Neural Networks
Biologically inspired spiking neural networks (SNNs) are widely used to realize ultralow-power energy consumption. However, deep SNNs are not easy to train due to the excessive firing of spiking neurons in the hidden layers. To tackle this problem, we propose a novel but simple normalization techniq...
Main Authors: | Ikegawa, S.-I (Author), Natori, N. (Author), Saiin, R. (Author), Sawada, Y. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2022
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
Rethinking the Role of Normalization and Residual Blocks for Spiking Neural Networks
by: Ikegawa, S.-I, et al.
Published: (2022) -
Compact Graphene-Based Spiking Neural Network With Unsupervised Learning Capabilities
by: He Wang, et al.
Published: (2020-01-01) -
Sparse Computation in Adaptive Spiking Neural Networks
by: Davide Zambrano, et al.
Published: (2019-01-01) -
Probabilistic Spike Propagation for Efficient Hardware Implementation of Spiking Neural Networks
by: Abinand Nallathambi, et al.
Published: (2021-07-01) -
Modified Elman Spike Neural Network for Identification and Control of Dynamic System
by: Nadia Adnan Shiltagh Al-Jamali, et al.
Published: (2020-01-01)