Saved in:
Bibliographic Details
Main Authors: La Bella, Alessio, Farina, Marcello, D'Amico, William, Zaccarian, Luca
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15792
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914955879514112
author La Bella, Alessio
Farina, Marcello
D'Amico, William
Zaccarian, Luca
author_facet La Bella, Alessio
Farina, Marcello
D'Amico, William
Zaccarian, Luca
contents In this paper we propose novel global and regional stability analysis conditions based on linear matrix inequalities for a general class of recurrent neural networks. These conditions can be also used for state-feedback control design and a suitable optimization problem enforcing H2 norm minimization properties is defined. The theoretical results are corroborated by numerical simulations, showing the advantages and limitations of the methods presented herein.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15792
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Regional stability conditions for recurrent neural network-based control systems
La Bella, Alessio
Farina, Marcello
D'Amico, William
Zaccarian, Luca
Systems and Control
In this paper we propose novel global and regional stability analysis conditions based on linear matrix inequalities for a general class of recurrent neural networks. These conditions can be also used for state-feedback control design and a suitable optimization problem enforcing H2 norm minimization properties is defined. The theoretical results are corroborated by numerical simulations, showing the advantages and limitations of the methods presented herein.
title Regional stability conditions for recurrent neural network-based control systems
topic Systems and Control
url https://arxiv.org/abs/2409.15792