Baruah, Sanjoy, Burns, Alan orcid.org/0000-0001-5621-8816 and Wu, Yue (2021) Optimal Synthesis of IDK-Cascades. In: RTNS'2021: 29th International Conference on Real-Time Networks and Systems. Real-Time Networked Systems, 07-09 Apr 2021 ACM , pp. 184-191.
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.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 Association for Computing Machinery. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 16 Feb 2022 11:50 |
Last Modified: | 04 Dec 2024 00:27 |
Published Version: | https://doi.org/10.1145/3453417.3453425 |
Status: | Published |
Publisher: | ACM |
Identification Number: | 10.1145/3453417.3453425 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:183643 |