Toward a spintronic deep learning spiking neural processor

Abhronil Sengupta, Bing Han, Kaushik Roy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

Deep Spiking neural architectures are becoming increasingly popular tools in complex pattern recognition tasks. However, implementation of such algorithms in conventional CMOS hardware entails huge area and power consumption due to the significant mismatch between the computational units and the corresponding CMOS devices. In this paper, we explore the design of an All-Spin Deep Spiking Neural Network where we demonstrate the mapping of synaptic and neuronal functionalities to domain wall dynamics in ferromagnets. We evaluate the potential advantages offered by such spintronic devices by performing micromagnetic simulations calibrated to experimental results. In order to investigate the benefits of such a spintronic design for large-scale neuromorphic systems, we perform device-circuit-algorithm co-design for a standard digit recognition problem on the MNIST dataset. Results indicate 250 × improvements in energy consumption and 56× improvement in EDP of the spintronic deep network over a baseline CMOS implementation in commercial 45nm technology.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 IEEE Biomedical Circuits and Systems Conference, BioCAS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages544-547
Number of pages4
ISBN (Electronic)9781509029594
DOIs
StatePublished - Jan 1 2016
Event12th IEEE Biomedical Circuits and Systems Conference, BioCAS 2016 - Shanghai, China
Duration: Oct 17 2016Oct 19 2016

Publication series

NameProceedings - 2016 IEEE Biomedical Circuits and Systems Conference, BioCAS 2016

Conference

Conference12th IEEE Biomedical Circuits and Systems Conference, BioCAS 2016
CountryChina
CityShanghai
Period10/17/1610/19/16

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Instrumentation
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Toward a spintronic deep learning spiking neural processor'. Together they form a unique fingerprint.

  • Cite this

    Sengupta, A., Han, B., & Roy, K. (2016). Toward a spintronic deep learning spiking neural processor. In Proceedings - 2016 IEEE Biomedical Circuits and Systems Conference, BioCAS 2016 (pp. 544-547). [7833852] (Proceedings - 2016 IEEE Biomedical Circuits and Systems Conference, BioCAS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BioCAS.2016.7833852