Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Galimberti, Clara"'
The growing scale and complexity of safety-critical control systems underscore the need to evolve current control architectures aiming for the unparalleled performances achievable through state-of-the-art optimization and machine learning algorithms.
Externí odkaz:
http://arxiv.org/abs/2405.00871
Autor:
Boroujeni, Mahrokh Ghoddousi, Galimberti, Clara Lucía, Krause, Andreas, Ferrari-Trecate, Giancarlo
Stochastic Nonlinear Optimal Control (SNOC) involves minimizing a cost function that averages out the random uncertainties affecting the dynamics of nonlinear systems. For tractability reasons, this problem is typically addressed by minimizing an emp
Externí odkaz:
http://arxiv.org/abs/2403.17790
Autor:
Martinelli, Daniele, Galimberti, Clara Lucía, Manchester, Ian R., Furieri, Luca, Ferrari-Trecate, Giancarlo
In this work, we introduce and study a class of Deep Neural Networks (DNNs) in continuous-time. The proposed architecture stems from the combination of Neural Ordinary Differential Equations (Neural ODEs) with the model structure of recently introduc
Externí odkaz:
http://arxiv.org/abs/2304.02976
We address the problem of designing stabilizing control policies for nonlinear systems in discrete-time, while minimizing an arbitrary cost function. When the system is linear and the cost is convex, the System Level Synthesis (SLS) approach offers a
Externí odkaz:
http://arxiv.org/abs/2203.11812
Large-scale cyber-physical systems require that control policies are distributed, that is, that they only rely on local real-time measurements and communication with neighboring agents. Optimal Distributed Control (ODC) problems are, however, highly
Externí odkaz:
http://arxiv.org/abs/2112.09046
Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the dis
Externí odkaz:
http://arxiv.org/abs/2105.13205
Training deep neural networks (DNNs) can be difficult due to the occurrence of vanishing/exploding gradients during weight optimization. To avoid this problem, we propose a class of DNNs stemming from the time discretization of Hamiltonian systems. T
Externí odkaz:
http://arxiv.org/abs/2104.13166
Autor:
Xu, Liang, Guo, Baiwei, Galimberti, Clara, Farina, Marcello, Carli, Ruggero, Trecate, Giancarlo Ferrari
Publikováno v:
In IFAC PapersOnLine 2020 53(2):11032-11037
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Large-scale cyber-physical systems require that control policies are distributed, that is, that they only rely on local real-time measurements and communication with neighboring agents. Optimal Distributed Control (ODC) problems are, however, highly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3419a9f8fbf75918a22be627e8992027
https://infoscience.epfl.ch/record/301740
https://infoscience.epfl.ch/record/301740