Saved in:
Bibliographic Details
Main Authors: Drummond, Ross, Guiver, Chris, Turner, Matthew C.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.19029
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909212745924608
author Drummond, Ross
Guiver, Chris
Turner, Matthew C.
author_facet Drummond, Ross
Guiver, Chris
Turner, Matthew C.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19029
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Convex neural network synthesis for robustness in the 1-norm
Drummond, Ross
Guiver, Chris
Turner, Matthew C.
Systems and Control
Artificial Intelligence
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.
title Convex neural network synthesis for robustness in the 1-norm
topic Systems and Control
Artificial Intelligence
url https://arxiv.org/abs/2405.19029