Drummond, R. orcid.org/0000-0002-2586-1718, Baldivieso-Monasterios, P.R. and Valmorbida, G. (2024) Mapping back and forth between model predictive control and neural networks. In: Proceedings of Machine Learning Research. 6th Annual Learning for Dynamics & Control Conference, 15-17 Jul 2024, Oxford, United Kingdom. ML Research Press , pp. 1228-1240.
Abstract
Model predictive control (MPC) for linear systems with quadratic costs and linear constraints is shown to admit an exact representation as an implicit neural network. A method to “unravel” the implicit neural network of MPC into an explicit one is also introduced. As well as building links between model-based and data-driven control, these results emphasize the capability of implicit neural networks for representing solutions of optimisation problems, as such problems are themselves implicitly defined functions.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 R. Drummond, P.R. Baldivieso-Monasterios & G. Valmorbida. |
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 16:01 |
Last Modified: | 17 Jan 2025 16:01 |
Published Version: | https://proceedings.mlr.press/v242/drummond24a.htm... |
Status: | Published |
Publisher: | ML Research Press |
Refereed: | Yes |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:221798 |