Baruah, Sanjoy, Burns, Alan orcid.org/0000-0001-5621-8816, Davis, Robert Ian orcid.org/0000-0002-5772-0928 et al. (1 more author) (2023) Optimally ordering IDK classifiers subject to deadlines. Real-Time Systems. ISSN 1573-1383
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.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © The Author(s) 2022 |
Keywords: | Deep Learning,Optimal synthesis,IDK cascades,Hard deadlines,Classifiers |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Funding Information: | Funder Grant number EPSRC EP/N023641/1 INNOVATE UK 113213/SUP-00007484 |
Depositing User: | Pure (York) |
Date Deposited: | 18 May 2022 09:20 |
Last Modified: | 21 Nov 2024 00:46 |
Published Version: | https://doi.org/10.1007/s11241-022-09383-w |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.1007/s11241-022-09383-w |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:187022 |
Download
Filename: Baruah2022_Article_OptimallyOrderingIDKClassifier.pdf
Description: Optimally ordering IDK classifers subject to deadlines
Licence: CC-BY 2.5