Robustness to training disturbances in SpikeProp Learning
Stability is a key issue during spiking neural network training using SpikeProp. The inherent nonlinearity of Spiking Neuron means that the learning manifold changes abruptly; therefore, we need to carefully choose the learning steps at every instance. Other sources of instability are the external d...
Saved in:
Main Authors: | Shrestha, Sumit Bam, Song, Qing |
---|---|
其他作者: | School of Electrical and Electronic Engineering |
格式: | Article |
語言: | English |
出版: |
2020
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/139881 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Surge in SpikeProp algorithm
由: Zhang, Zhengyang
出版: (2014) -
Supervised learning in multilayer spiking neural network
由: Shrestha, Sumit Bam
出版: (2017) -
Capacity of rate adaptive MQAM systems in the presence of channel estimation errors under BER constraint
由: Mo, R., et al.
出版: (2014) -
Inductive robust principal component analysis
由: Bao, B.-K., et al.
出版: (2014) -
Automatic Spike sorting and robust power line interference cancellation for neural signal processing
由: MOHAMMADREZA KESHTKARAN
出版: (2014)