Details of the talk:
- Date: June 13, 2024
- Time: 11:00 a.m. - 12:00 p.m.
- Location: Ground-floor lecture hall, Tübingen AI Center (Maria-von-Linden-Str. 6, 72076 Tübingen)
Talk title: Graph neural networks for numerical linear algebra
Abstract: Numerical linear algebra underpins all computational sciences, machine learning not the least. But what if machine learning could return the favor by learning numerical algorithms tailored to a particular problem class? In this talk, I will highlight the connection between matrices and graphs, and argue that this makes graph neural networks a natural fit for learning task-specific numerical algorithms.
Bio: Jens Sjölund is an assistant professor in Artificial Intelligence (AI) at Uppsala University, Sweden. His research interests are primarily in machine learning and optimization, and how such methods can support research in the natural sciences (AI4Science). Prior to joining Uppsala University, Sjölund was a senior research scientist working on machine learning, optimization, and medical image analysis at the radiotherapy company Elekta, where he did an industrial PhD affiliated with Linköping University.