Optimal Synthesis of IDK-Cascades

  • Sanjoy Baruah
  • , Alan Burns
  • , Yue Wu

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

11 Scopus citations

Abstract

A classifier is a software component, often based upon deep learning (DL), that categorizes each input provided to it into one of a fixed set of "classes". An IDK classifier may additionally output an "I don't know"(IDK) on certain input. Given several different IDK classifiers for the same operation, the problem is considered of using them in concert in such a manner that the average duration to successfully classify any input is minimized. Optimal algorithms are proposed for solving this problem, both as is and under an additional constraint that the operation must be completed within a specified hard deadline).

Original languageEnglish
Title of host publicationRTNS 2021 - 29th International Conference on Real-Time Networks and Systems
PublisherAssociation for Computing Machinery
Pages184-191
Number of pages8
ISBN (Electronic)9781450390019
DOIs
StatePublished - Apr 7 2021
Event29th International Conference on Real-Time Networks and Systems, RTNS 2021 - Nantes, France
Duration: Apr 7 2021 → …

Publication series

NameACM International Conference Proceeding Series

Conference

Conference29th International Conference on Real-Time Networks and Systems, RTNS 2021
Country/TerritoryFrance
CityNantes
Period04/7/21 → …

Keywords

  • Classifiers
  • Deep Learning
  • Hard deadlines
  • IDK-Cascades
  • Optimal Synthesis

Fingerprint

Dive into the research topics of 'Optimal Synthesis of IDK-Cascades'. Together they form a unique fingerprint.

Cite this