Dear all,
At CWI, we are organizing a seminar on Machine Learning and Uncertainty Quantification for Scientific Computing. Next Thursday (the 11th) at 15h30 we will have the next speaker. Benjamin Sanderse will talk about multi-level neural networks for partial differential equations with uncertain parameters. You can find the zoom link and the abstract below. We hold talks about twice a month, with both internal and external speakers. More information can be found here: https://www.cwi.nl/research/groups/scientific-computing/uq-seminar/seminar-m..., which is updated regularly.
Best regards,
Wouter Edeling
https://cwi-nl.zoom.us/j/9201774084?pwd=OFBqM1dUenFreGdPUWEwZFYvMlJ6UT09
11 Mar. 2021 15h30: Benjamin Sanderse (CWI): Multi-Level Neural Networks for PDEs with Uncertain Parameters
A novel multi-level method for partial differential equations with uncertain parameters is proposed. The principle behind the method is that the error between grid levels in multi-level methods has a spatial structure that is by good approximation independent of the actual grid level. Our method learns this structure by employing a sequence of convolutional neural networks, that are well-suited to automatically detect local error features as latent quantities of the solution. Furthermore, by using the concept of transfer learning, the information of coarse grid levels is reused on fine grid levels in order to minimize the required number of samples on fine levels. The method outperforms state-of-the-art multi-level methods, especially in the case when complex PDEs (such as single-phase and free-surface flow problems) are concerned, or when high accuracy is required.