Spiking Neural Network Based Low-Power Radioisotope Identification using FPGA

作者：Xiaoyu Huang, Edward Jones, Siru Zhang, Shouyu Xie, Steve Furber, Yannis Goulermas, Edward Marsden, Ian Baistow, Srinjoy Mitra, Alister Hamilton · 年份：2020 · DOI：10.1109/icecs49266.2020.9294873 · 被引用次数：6 · 研究领域：Advanced Memory and Neural Computing、CCD and CMOS Imaging Sensors、Semiconductor materials and devices

This paper presents detailed methodology of a Spiking Neural Network (SNN) based low-power design for radioisotope identification. A low power cost of 72 m W 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.