Optimally ordering IDK classifiers subject to deadlines

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 classi...

Full description

Saved in:
Bibliographic Details
Published inReal-time systems Vol. 59; no. 1; pp. 1 - 34
Main Authors Baruah, Sanjoy, Burns, Alan, Davis, Robert I., Wu, Yue
Format Journal Article
LanguageEnglish
Published New York Springer US 01.03.2023
Subjects
Communications Engineering
Computer Science
Computer Systems Organization and Communication Networks
Control
Mechatronics
Networks
Performance and Reliability
Robotics
Special Purpose and Application-Based Systems
Classifiers
Hard deadlines
Deep Learning
Optimal synthesis
IDK cascades
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:0922-6443
1573-1383
DOI:10.1007/s11241-022-09383-w