[Dottorcomp] Reminder for Today PAV-IA Reading Seminar : "Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning" Tim De Ryck and Siddhartha Mishra
Siam Student Chapter
siamstudentchapter a unipv.it
Mar 28 Gen 2025 08:18:52 CET
Dear all,
This is a gentle reminder about *Today's* Seminar of PAV-IA, from *13:00 to
14:00 *at the Department of Mathematics in Aula Beltrami.
*The upcoming seminar will be different from the typical PAV-IA seminar,
this will be our first "Reading seminar". Which means that **the speaker
will present and discuss an article of interest*
*, instead of giving an introduction to a general topic. *
*Upcoming Seminar:*
- *Title: *Numerical analysis of physics-informed neural networks and
related models in physics-informed machine learning
<https://www.cambridge.org/core/journals/acta-numerica/article/numerical-analysis-of-physicsinformed-neural-networks-and-related-models-in-physicsinformed-machine-learning/A059C6E13478F0F7C70EC7C976716F9F>
.
- *Authors: *Tim De Ryck and Siddhartha Mishra.
- *Speaker*: Luca Pellegrini.
- *Description*: This article aims to provide a comprehensive review of
currently available results on the numerical analysis of PINNs
<https://www.sciencedirect.com/science/article/pii/S0021999118307125>
and related models that constitute the backbone of physics-informed
machine learning. We provide a unified framework in which analysis of the
various components of the error incurred by PINNs in approximating PDEs can
be effectively carried out.
- *Where and when: *Tuesday, January 28th, from 13:00 to 14:00 , at the
Aula Beltrami, Department of Mathematics, University of Pavia.
*If you haven't already done so, please fill out this short form
<https://docs.google.com/forms/d/1-kH0a4VIVMZLOzGN0CHFN4Bi6A861IPLv8-9wN3Vk6c/edit>
to attend.*
We look forward to your participation!
Stay updated on SIAM Chapter activities by visiting our website
<https://sites.google.com/view/siam-unipv/home>.
Sincerely,
Luca and Massimiliano
Maggiori informazioni sulla lista
Dottorcomp