Please log in to watch this conference skillscast.
Many scientific applications currently rely on the use of brute-force numerical methods performed on high-performance computing (HPC) infrastructure. However, these methods have their limits in many applications, e.g. climate prediction. Can artificial intelligence (AI) methods augment or even entirely replace these brute-force calculations to obtain significant speed-ups? Anima will present exciting recent advances that build new foundations in AI, viz. neural operators that are independent of the resolution or grid of training data and allow for zero-shot generalization to higher resolution evaluations. They have recently yielded 4-5 orders of magnitude speedups over standard numerical weather models.
Heralding Scientific Breakthroughs Through AI At Supercomputing Scale
Animashree Anandkumar
Bren Professor
AAIA, IEEE, Microsoft and Sloan Fellow
Computing + Mathematical Sciences
California Institute of Technology