Alpizar Santana, Misael, Calinescu, Radu orcid.org/0000-0002-2678-9260 and Paterson, Colin orcid.org/0000-0002-6678-3752 (2022) Mitigating Risk in Neural Network Classifiers. In: 48th Euromicro Conference Series on Software Engineering and Advanced Applications (SEAA). IEEE
Abstract
Deep Neural Network (DNN) classifiers perform remarkably well on many problems that require skills which are natural and intuitive to humans. These classifiers have been used in safety-critical systems including autonomous vehicles. For such systems to be trusted it is necessary to demonstrate that the risk factors associated with neural network classification have been appropriately considered and sufficient risk mitigation has been employed. Traditional DNNs fail to explicitly consider risk during their training and verification stages, meaning that unsafe failure modes are permitted and under-reported. To address this limitation, our short paper introduces a work-in-progress approach that (i) allows the risk of misclassification between classes to be quantified, (ii) guides the training of DNN classifiers towards mitigating the risks that require treatment, and (iii) synthesises risk-aware ensembles with the aid of multi-objective genetic algorithms that seek to optimise DNN performance metrics while also mitigating risks. We show the effectiveness of our approach by using it to synthesise risk-aware neural network ensembles for the CIFAR-10 dataset.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | 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 |
Keywords: | deep neural network, risk, risk mitigation |
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/V026747/1 |
Depositing User: | Pure (York) |
Date Deposited: | 16 Jun 2022 15:00 |
Last Modified: | 23 Dec 2024 00:05 |
Status: | Published |
Publisher: | IEEE |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:188121 |
Download
Filename: SEAA2022_Mitigating_Riskpdf.pdf
Description: SEAA2022-Mitigating-Riskpdf