Publications associées à Nonlinear system identification

Koopman-based Data-driven Robust Control of Nonlinear Systems Using Integral Quadratic Constraints

This paper introduces a novel method for data-driven robust control of nonlinear systems based on the Koopman operator, utilizing Integral Quadratic Constraints (IQCs). The Koopman operator theory facilitates the linear representation of nonlinear system d ...

2024

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Marco Picasso, Maude Girardin, Alexandre Caboussat

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Elsevier Science Sa2024

Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations

Giancarlo Ferrari Trecate, Luca Furieri, Daniele Martinelli, Clara Lucía Galimberti

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 introduced Rec ...

IEEE2023

Backpropagation-free training of deep physical neural networks

Romain Christophe Rémy Fleury, Ali Momeni, Babak Rahmani, Matthieu Francis Malléjac, Marc Philipp Del Hougne

Recent successes in deep learning for vision and natural language processing are attributed to larger models but come with energy consumption and scalability issues. Current training of digital deep-learning models primarily relies on backpropagation that ...

American Association for the Advancement of Science2023

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Elisabetta Cornacchia

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

EPFL2023

Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems

Colin Neil Jones, Roland Schwan, Melanie Nicole Zeilinger, Xuan Truong Nghiem

Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to ...

IEEE2023

Closed-loop data-driven modeling and distributed control for islanded microgrids with input constraints

Alireza Karimi, Seyed Sohail Madani, Dongdong Zheng

In this paper a new nonlinear identification method for microgrids based on neural networks is proposed. The system identification process can be done using the available closed-loop system input/output data recorded during normal operation without additio ...

PERGAMON-ELSEVIER SCIENCE LTD2022

Local Kernel Regression and Neural Network Approaches to the Conformational Landscapes of Oligopeptides

Michele Ceriotti, Anne-Clémence Corminboeuf, Alberto Fabrizio, Benjamin André René Meyer, Edgar Albert Engel, Raimon Fabregat I De Aguilar-Amat, Veronika Juraskova

The application of machine learning to theoretical chemistry has made it possible to combine the accuracy of quantum chemical energetics with the thorough sampling of finite-temperature fluctuations. To reach this goal, a diverse set of methods has been pr ...

2022

Control-oriented modeling and analysis of tubular dielectric elastomer actuators dedicated to cardiac assist devices

Yves Perriard, Yoan René Cyrille Civet, Thomas Guillaume Martinez, Armando Matthieu Walter, Ning Liu

This paper deals with the control-oriented modeling of a multilayered dielectric elastomer actuator based tube. The actuator is clamped at both sides and performs a radial displacement. The hyperelastic deformation and the viscoelastic performance, togethe ...

2022

Controllability and Interpretability in Affective Speech Synthesis

Bastian Schnell

Thanks to Deep Learning Text-To-Speech (TTS) has achieved high audio quality with large databases. But at the same time the complex models lost any ability to control or interpret the generation process. For the big challenge of affective TTS it is infeasi ...

EPFL2022