By the same authors

From the same journal

From the same journal

Optimally ordering IDK classifiers subject to deadlines

Research output: Contribution to journalArticlepeer-review

Full text download(s)

Published copy (DOI)

Author(s)

Department/unit(s)

Publication details

JournalReal-Time Systems
DateAccepted/In press - 10 Apr 2022
DateE-pub ahead of print (current) - 14 May 2022
Number of pages34
Early online date14/05/22
Original languageEnglish

Abstract

A classifier is a software component, often based on Deep Learning, that categorizes each input provided to it into one of a fixed set of classes. An IDK classifier may additionally output “I Don’t Know” (IDK) for certain inputs. Multiple distinct IDK classifiers may be available for the same classification problem, offering different trade-offs between effectiveness, i.e. the probability of successful classification, and efficiency, i.e. execution time. Optimal offline algorithms are proposed for sequentially ordering IDK classifiers such that the expected duration to successfully classify an input is minimized, optionally subject to a hard deadline on the maximum time permitted for classification. Solutions are provided considering independent and dependent relationships between pairs of classifiers, as well as a mix of the two.

Bibliographical note

© The Author(s) 2022

    Research areas

  • Deep Learning, Optimal synthesis, IDK cascades, Hard deadlines, Classifiers

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations