BROWSE
Detail
Conference Paper
Optimizing Implementation of SNN for Embedded System
Cited 0 time in 
Share 
Share
- Authors
- Hyeonguk Jang, Jae-Jin Lee, Kyuseung Han
- Issue Date
- 2024-02
- Citation
- International Conference on Advanced Communications Technology (ICACT) 2024, pp.104-106
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Spiking neural networks (SNNs) are a highly promising AI technology for embedded systems, owing to their energy-efficient properties. However, the manual implementation of SNNs encounters practical challenges because of the all-to-all connections in large networks. Thus, this paper presents a novel methodology to reduce wire congestion in the SNN implementations while mitigating adverse effects on inference accuracy.
- KSP Keywords
- Adverse effects, Large network, Wire congestion, all-to-all, embedded system, energy-efficient, neural network(NN), spiking neural networks