The Computing Division Technical Meetings are a platform for

  • presenting Pinboard papers under review for journal or conference publication,
  • inviting speakers who are current or prospective UKAEA collaborators at external organisations,
  • presenting work done in PhD projects funded by or co-supervised by UKAEA,
  • presenting work done during summer placements or other secondments to UKAEA.

 

If you would like to invite a speaker on a topic that would be of interest to one or more Units within the Computing Division, but is not currently collaborating on a UKAEA project, please consider nominating them for a Computing Division Cross-Disciplinary Seminar.

These meetings are normally recorded. Recordings of past meetings can be found here:

CD Technical Meetings Archive on UKAEA Sharepoint

CD Technical Meeting (ML11): Neural and hybrid methods for high-dimensional PDEs

→ Europe/London
Emmanuel Franck (Institut de Recherche Mathématique Avancée)
Description
Machine Learning, Uncertainty Quantification and Data Science 

 

In this presentation, we will introduce a common framework between standard numerical methods and recent approaches based on neural networks. From there, we will propose a numerical method for solving large-scale transport PDEs like Vlasov-Poisson equation. Next, we will present results on hybrid methods combining the two approaches to obtain accuracy and some  convergence results. To finish we will discuss future development to solve high-dimensional PDEs.

Join Meeting Now (Teams)