Real-Time Scheduling of Multistage IDK-Cascades

Sanjoy Baruah

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

3 Scopus citations

Abstract

An IDK classifier is a software component that categorizes each input provided to it into one of a fixed set of 'classes,' or outputs an 'I don't know' (IDK) to indicate that it is unable to classify this input. An IDK-cascade is a linear arrangement of different IDK classifiers for the same classification problem, which are executed in sequence on a given input until one outputs an actual class (rather than IDK). Given a multistage computation that must be completed within a specified hard end-to-end deadline and a choice of classifiers, one deterministic and one an IDK-cascade, for each stage, the problem of determining which IDK-cascades to schedule in order to minimize the expected end-to-end response time while guaranteeing to meet the specified deadline is considered. Different variants of this problem are defined, and optimal algorithms for solving them are derived.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 24th International Symposium on Real-Time Distributed Computing, ISORC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages79-85
Number of pages7
ISBN (Electronic)9781665404143
DOIs
StatePublished - Jun 2021
Event24th IEEE International Symposium on Real-Time Distributed Computing, ISORC 2021 - Virtual, Daegu, Korea, Republic of
Duration: Jun 1 2021Jun 3 2021

Publication series

NameProceedings - 2021 IEEE 24th International Symposium on Real-Time Distributed Computing, ISORC 2021

Conference

Conference24th IEEE International Symposium on Real-Time Distributed Computing, ISORC 2021
Country/TerritoryKorea, Republic of
CityVirtual, Daegu
Period06/1/2106/3/21

Keywords

  • Classifiers
  • Deep Learning
  • End-to-end Deadline
  • IDK-cascades
  • Multistage Computation

Fingerprint

Dive into the research topics of 'Real-Time Scheduling of Multistage IDK-Cascades'. Together they form a unique fingerprint.

Cite this