An Event-Driven Recurrent Spiking Neural Network Architecture for Efficient Inference on FPGA

Anand Sankaran, Paul Detterer, Kalpana Kannan, Nikolaos Alachiotis, Federico Corradi

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

4 Citations (Scopus)
151 Downloads (Pure)

Abstract

Spiking Neural Network (SNN) architectures are promising candidates for executing machine intelligence at the edge while meeting strict energy and cost reduction constraints in several application areas. To this end, we propose a new digital architecture compatible with Recurrent Spiking Neural Networks (RSNNs) trained using the PyTorch framework and Back-Propagation-Through-Time (BPTT) for optimizing the weights and the neuron’s parameters. Our architecture offers high software-to-hardware fidelity, providing high accuracy and a low number of spikes, and it targets efficient and low-cost implementations in Field Programmable Gate Arrays (FPGAs). We introduce a new time-discretization technique that uses request-acknowledge cycles between layers to allow the layer’s time execution to depend only upon the number of spikes. As a result, we achieve between 1.7x and 30x lower resource utilization and between 11x and 61x fewer spikes per inference than previous SNN implementations in FPGAs that rely on on-chip memory to store spike-time information and weight values. We demonstrate our approach using two benchmarks: MNIST digit recognition and a realistic radar and image sensory fusion for cropland classifications. Our results demonstrate that we can exploit the trade-off between accuracy, latency, and resource utilization at design time. Moreover, the use of low-cost FPGA platforms enables the deployment of several applications by satisfying the strict constraints of edge machine learning devices.
Original languageEnglish
Title of host publicationICONS '22: Proceedings of the International Conference on Neuromorphic Systems 2022
Place of PublicationNew York, NY, USA
PublisherAssociation for Computing Machinery, Inc
Pages1-8
ISBN (Electronic)9781450397896
ISBN (Print)9781450397896
DOIs
Publication statusPublished - 27 Jul 2022
Event2022 International Conference on Neuromorphic Systems, ICONS 2022 - Knoxville, United States
Duration: 27 Jul 202229 Jul 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2022 International Conference on Neuromorphic Systems, ICONS 2022
Country/TerritoryUnited States
CityKnoxville
Period27/07/2229/07/22

Keywords

  • spiking neural networks
  • embedded hardware
  • FPGA

Fingerprint

Dive into the research topics of 'An Event-Driven Recurrent Spiking Neural Network Architecture for Efficient Inference on FPGA'. Together they form a unique fingerprint.

Cite this