Noise-Robust Deep Spiking Neural Networks with Temporal Information
This addresses noise robustness for deep SNNs with temporal information, which is incremental as it builds on prior work but focuses on deeper networks and temporal aspects.
The paper tackles the problem of noise susceptibility in deep spiking neural networks (SNNs) on neuromorphic devices, achieving an efficient and robust SNN that handles spike deletion and jitter.
Spiking neural networks (SNNs) have emerged as energy-efficient neural networks with temporal information. SNNs have shown a superior efficiency on neuromorphic devices, but the devices are susceptible to noise, which hinders them from being applied in real-world applications. Several studies have increased noise robustness, but most of them considered neither deep SNNs nor temporal information. In this paper, we investigate the effect of noise on deep SNNs with various neural coding methods and present a noise-robust deep SNN with temporal information. With the proposed methods, we have achieved a deep SNN that is efficient and robust to spike deletion and jitter.