16 gennaio 2025 | 11:30
Dipartimento di Elettronica, Informazione e Bioingegneria - Politecnico di Milano
Sala conferenze Emilio Gatti (Edificio 20)
Speaker: Lapo Frascati (Politecnico di Milano)
Contatti: Prof. Simone Formentin | simone.formentin@polimi.it
Sommario
In the development of Model Predictive Control (MPC) systems, having a data-driven approach to automatically identify black-box dynamical models that are both accurate and computationally efficient is of paramount importance. A novel learning procedure which is capable to automatically reduce the state/model size during the training phase by employing RESNETs and Group Lasso will be described, along with some results on a few benchmark examples.
