Skip to main navigation Skip to search Skip to main content

Robustly executing DNNs in IoT systems using coded distributed computing

  • Georgia Institute of Technology

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

17 Scopus citations

Abstract

Internet of Things (IoT) devices have access to an abundance of raw data for processing. With deep neural networks (DNNs), not only the demand for the computing power of IoT devices is increasing, but also privacy concerns are motivating the importance of close-toedge computation. DNN execution by distributing its computation is common in IoT systems. However, managing unstable latencies in a network and intermittent failures are serious challenges. Our work provides robustness and close-to-zero recovery latency by adapting coded distributed computing (CDC). We analyze robust execution on a mesh of Raspberry Pis by studying four DNNs.

Original languageEnglish
Title of host publicationProceedings of the 56th Annual Design Automation Conference 2019, DAC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781450367257
DOIs
StatePublished - Jun 2 2019
Event56th Annual Design Automation Conference, DAC 2019 - Las Vegas, United States
Duration: Jun 2 2019Jun 6 2019

Publication series

NameProceedings - Design Automation Conference
ISSN (Print)0738-100X

Conference

Conference56th Annual Design Automation Conference, DAC 2019
Country/TerritoryUnited States
CityLas Vegas
Period06/2/1906/6/19

Fingerprint

Dive into the research topics of 'Robustly executing DNNs in IoT systems using coded distributed computing'. Together they form a unique fingerprint.

Cite this