SpArNet: Sparse Asynchronous Neural Network execution for energy efficient inference

Mina A. Khoei, Amirreza Yousefzadeh, Arash Pourtaherian, Orlando Moreira, Jonathan Tapson

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

Abstract

Biological neurons are known to have sparse and asynchronous communications using spikes. Despite our incomplete understanding of processing strategies of the brain, its low energy consumption in fulfilling delicate tasks suggests the existence of energy efficient mechanisms. Inspired by these key factors, we introduce SpArNet, a bio-inspired quantization scheme to convert a pre-trained convolutional neural network to a spiking neural network, with the aim of minimizing the computational load for execution on neuromorphic processors. The proposed scheme has significant advantages over the reference CNN in a reduced number of synaptic operations, and can be used for frequent executions of inference tasks. The computational load of SpArNet is adjusted to the spatio-temporal dynamics of the the input data. We have tested the converted network on two applications (autonomous steering and hand gesture recognition), demonstrating a significant reduction on the number of required synaptic operations.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020
PublisherInstitute of Electrical and Electronics Engineers
Pages256-260
Number of pages5
ISBN (Electronic)9781728149226
DOIs
Publication statusPublished - Aug 2020
Event2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020 - Genova, Italy
Duration: 31 Aug 20202 Sep 2020

Conference

Conference2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020
CountryItaly
CityGenova
Period31/08/202/09/20

Fingerprint Dive into the research topics of 'SpArNet: Sparse Asynchronous Neural Network execution for energy efficient inference'. Together they form a unique fingerprint.

  • Cite this

    Khoei, M. A., Yousefzadeh, A., Pourtaherian, A., Moreira, O., & Tapson, J. (2020). SpArNet: Sparse Asynchronous Neural Network execution for energy efficient inference. In Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020 (pp. 256-260). [9073827] Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/AICAS48895.2020.9073827