University of Cambridge > > Data Intensive Science Seminar Series > AI + HPC for Astrophysics

AI + HPC for Astrophysics

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact James Fergusson.

Can we already use AI as a new tool to do research in astrophysics? The answer to this question depends on whether we can map our astrophysical problems to AI problems. Existing AI algorithms/models driven by industrial developers can indeed be used to tackle some (but not all) astrophysical problems that are data-intensive, compute-intensive, or both. Nevertheless, due to the unique properties of physics data, adapting AI for astrophysics is by no means frictionless. In this talk, I will review the journey of astrophysical research from analytical models to empirical models, to data-driven discovery of physical laws, and eventually to augmenting AI models with inductive biases. I will also talk about upscaling AI models to massively parallel computers, an interplay of HPC and AI that makes training large models and ingesting huge datasets possible.

This talk is part of the Data Intensive Science Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity