-
Learning functions, operators and dynamical systems
Il giorno mercoledì 14 Giugno 2023, alle ore 10:30, Lorenzo Rosasco (Università di Genova) terrà un Colloquium del Dipartimento di Matematica e Applicazioni dal titolo
"Learning functions, operators and dynamical systems "
Il Colloquium si terrà in aula U3-01 (piazza della Scienza)
Segue l’abstract e una breve biografia dell'autore
Tutti gli interessati sono invitati a partecipare!
ABSTRACT: In this talk, I will first review some basic results on learning scalar functions in an optimal and efficient way using kernel methods. Then, I’ll discuss the extension of these results to learning linear and non linear operators. Finally, I will discuss the problem of learning dynamical systems by estimating the corresponding Koopman operators.
BiO: Lorenzo Rosasco is a professor at the University of Genova. He also holds a visiting professorship at the Massachusetts Institute of Technology (MIT) and he is visiting scientist at the Italian Technological Institute (IIT). He is a founder and serves as a coordinator of the Machine Learning Genova center (MaLGa) and the Laboratory for Computational and Statistical Learning, focusing on the theory, algorithms, and applications of machine learning. He obtained his PhD in 2006 from the University of Genova and has conducted research as a visiting student at the Center for Biological and Computational Learning at MIT, the Toyota Technological Institute at Chicago (TTI-Chicago), and the Johann Radon Institute for Computational and Applied Mathematics. From 2006 to 2013, he worked as a postdoc and research scientist at the Brain and Cognitive Sciences Department at MIT. He is a fellow at Ellis and serves as the co-director of the "Theory, Algorithms and Computations of Modern Learning Systems" program as well as the Ellis Genoa unit. Lorenzo has received several awards, including an ERC consolidator grant.
Argomento