Journal
ICT EXPRESS
Volume 7, Issue 2, Pages 152-157Publisher
ELSEVIER
DOI: 10.1016/j.icte.2021.05.003
Keywords
Edge device; Embedded systems; Edge AI; Neuromorphic technology; Training time
Funding
- MSIT, South Korea, under the Grand Information Technology Research Center support program [IITP-2020-2020-0-01612]
- National Research Foundation of Korea (NRF) - Ministry of Education, South Korea [2018R1A6A1A03024003, 2019R1I1A1A01063895]
Ask authors/readers for more resources
This study presents a test bed demonstration of NeuroEdge computing for face recognition using a novel neuromorphic chip (NM500). The neuromorphic technology offers scalability and consistent recognition time, making it advantageous for real-time networked systems. The results showed that using neuromorphic technology can save training time and does not require a large dataset for effective training.
This paper presents a test bed demonstration of NeuroEdge computing for face recognition using a novel neuromorphic chip-NM500. First, a general description and important specifications of the NM500 are presented. Second, a face recognition test-bed case study is used to demonstrate the efficacy and efficiency of the chip. Neuromorphic technology offers scalability and consistent recognition time, which is required by real-time networked systems, and presents a considerable advantage for real-time computations, making them virtually independent of the dataset size. In this study, intelligent edge computing technology was introduced using NeuroEdge. The performance was verified using a face recognition test. The results demonstrated that using neuromorphic technology, such as the NM500 chip, saves the time needed for training systems and does not impose the burden of requiring many datasets for effective training. (C) 2021 The Korean Institute of Communications and Information Sciences (KICS). Publishing Services by Elsevier B.V.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available