Robustness to training disturbances in SpikeProp Learning

• Main Authors: Shrestha, Sumit Bam, Song, Qing
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2020
• Subjects: Engineering::Electrical and electronic engineering; Adaptive Learning Rate; Error Analysis
• Online Access: https://hdl.handle.net/10356/139881
• Institution: Nanyang Technological University

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...