Drummond, R. orcid.org/0000-0002-2586-1718, Guiver, C. and Turner, M.C. (2024) Convex neural network synthesis for robustness in the 1-norm. In: Proceedings of Machine Learning Research. 6th Annual Learning for Dynamics & Control Conference, 15-17 Jul 2024, Oxford, United Kingdom. ML Research Press , pp. 1388-1399.
Abstract
With neural networks being used to control safety-critical systems, they increasingly have to be both accurate (in the sense of matching inputs to outputs) and robust. However, these two properties are often at odds with each other and a trade-off has to be navigated. To address this issue, this paper proposes a method to generate an approximation of a neural network which is certifiably more robust. Crucially, the method is fully convex and posed as a semi-definite programme. An application to robustifying model predictive control is used to demonstrate the results. The aim of this work is to introduce a method to navigate the neural network robustness/accuracy trade-off.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 R. Drummond, C. Guiver & M.C. Turner. |
Keywords: | Neural network robustness; convex synthesis; accuracy vs. robustness trade-off |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > School of Electrical and Electronic Engineering |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 17 Jan 2025 15:05 |
Last Modified: | 17 Jan 2025 15:05 |
Status: | Published |
Publisher: | ML Research Press |
Refereed: | Yes |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:221801 |