New avenues for the interaction of computational mechanics and machine learning
FAU MoD Lecture: New avenues for the interaction of computational mechanics and machine learning
Date: Thu. October 24, 2024
Event: FAU MoD Lecture
Organized by: FAU MoD, the Research Center for Mathematics of Data at Friedrich-Alexander-Universitat Erlangen-Nürnberg (Germany)
FAU MoD Lecture: New avenues for the interaction of computational mechanics and machine learning
Speaker: Prof. Dr. Paolo Zunino
Affiliation: MOX, Politecnico di Milano (Italy)
Abstract. Neural networks and learning algorithms have gained substantial attention among researchers engaged in computational mechanics. Notably, there are well-established methodologies for employing these tools in solving mathematical models based on partial differential equations. Additionally, a significant overlap exists between the machine learning and computational science and engineering communities in the realm of data-driven reduced order models. After reviewing the main trends in this field, we will discuss novel emerging approaches such as the application of learning algorithms to expedite the resolution of linear systems or to foster the approximation of multiscale problems.
See poster
BIO.- Paolo Zunino is Full Professor in Numerical Analysis at the laboratory of Modeling and Scientific Computing (MOX), Department of Mathematics, Politecnico di Milano. His research interests concern the development of numerical methods for partial differential equations, with focus on multiscale and reduced order models applied to life sciences. He is particularly interested in coupled problems involving lower dimensional manifolds, generally called mixed-dimensional partial differential equations. More recently he has successfully applied data-driven model reduction techniques to accelerate the numerical approximation of these models, making them available in real time, an enabling technology for the development of digital twins. These models have been instrumental in studying the impact of treatments like radiotherapy, chemotherapy, and immunotherapy. He has co-authored more than 130 publications on mathematical modeling and computational methods applied various fields of engineering and life sciences.
AUDIENCE
This is a hybrid event (On-site/online) open to: Public, Students, Postdocs, Professors, Faculty, Alumni and the scientific community all around the world.
WHEN
Thu. October 24, 2024 at 14:30H (Berlin time)
WHERE
On-site / Online
[On-site] Friedrich-Alexander-Universitat Erlangen-Nürnberg.
Room H2 (11202.00.305)
H2 Egerlandstr.3 Anorganische Chemie
Egerlandstrasse 3, 91058 Erlangen
GPS-Koord. Raum: 49.574538N, 11.028194E
[Online] FAU Zoom link
Meeting ID: 680 1463 6900 | PIN code: 222990
--
FROM 211.161.214.*