A parameterised family of neuralODEs optimally fitting steady-state data
Author(s)
Shakib, Mohammad Fahim
Scarciotti, Giordano
Astolfi, Alessandro
Type
Conference Paper
Abstract
This paper presents a parameterised family of neural ordinary differential equations (neuralODEs) that fit the steady-state system response in a least-squares sense. The family of neuralODEs is cast in the form of recurrent equilibrium networks (NodeRENs). One of the main advantages of the proposed approach is that it uses only linear least-squares optimisation tools. As such, the solution to the steady-state fitting problem is given in a closed-form expression. Furthermore, the NodeREN family leaves a subset of parameters free. This is useful for enforcing robustness or for fitting transient data in addition to steady-state data.
Date Issued
2024-09-05
Date Acceptance
2024-01-23
Citation
2024 American Control Conference (ACC), 2024
ISBN
979-8-3503-8265-5
ISSN
2378-5861
Publisher
IEEE
Journal / Book Title
2024 American Control Conference (ACC)
Copyright Statement
Copyright © 2024 AACC via IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
Identifier
https://ieeexplore.ieee.org/abstract/document/10644957
Source
2024 American Control Conference
Publication Status
Published
Start Date
2024-07-10
Finish Date
2024-07-12
Coverage Spatial
Toronto, Canada
Date Publish Online
2024-09-05