An FPGA Implementation of Convolutional Spiking Neural Networks for Radioisotope Identification

Abstract

This paper details the FPGA implementation methodology for Convolutional Spiking Neural Networks (CSNN) and applies this methodology to low-power radioisotope identification using high-resolution data. Power consumption of 75 mW has been achieved on an FPGA implementation of a CSNN, with an inference accuracy of 90.62% on a synthetic dataset. The chip validation method is presented. Prototyping was accelerated by evaluating SNN parameters using SpiNNaker neuromorphic platform.

5 pages, 10 FIGURES, IEEE ISCAS 2021

Cited by in corpus (1)

• FeSHI: Feature Map Based Stealthy Hardware Intrinsic Attack