South Korea, Samsung, Hyundai + Neuromorphic Chips, page-415

https://arxiv.org/abs/2104.11169

Noise-Robust Deep Spiking Neural Networks with Temporal Information

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.


This work was supported in part by the National Research Founda-tion of Korea (NRF) grant funded by the Korea government (Ministryof Science and ICT) [2016M3A7B4911115, 2018R1A2B3001628,2021R1C1C2010454], the Brain Korea 21 Plus Project in 2021, AIRSCompany in Hyundai Motor Company & Kia Motors Corporationthrough HKMC-SNU AI Consortium Fund, and Samsung ResearchFunding & Incubation Center of Samsung Electronics under ProjectNumber SRFC-IT1901-12.