this paper presents a detailed methodology of a Spiking Neural Network (SNN) based low-power design for radioisotope identification. A low power cost of 72 mW has been achieved on FPGA with the inference accuracy of 100% at 10 cm test distance and 97% at 25 cm. The design verification and chip validation methods are presented. It also discusses SNN simulation on SpiNNaker for rapid prototyping and various considerations specific to the application such as test distance, integration time, and SNN hyperparameter selections.
@article{arxiv.2010.13125,
title = {Spiking Neural Network Based Low-Power Radioisotope Identification using FPGA},
author = {Xiaoyu Huang and Edward Jones and Siru Zhang and Shouyu Xie and Steve Furber and Yannis Goulermas and Edward Marsden and Ian Baistow and Srinjoy Mitra and Alister Hamilton},
journal= {arXiv preprint arXiv:2010.13125},
year = {2020}
}
Comments
4 pages, 10 figures, 27th IEEE International Conference on Electronics Circuits and Systems (ICECS) 2020