Explore groundbreaking advancements in AI for scientific applications in this 52-minute webinar presented by Anima Anandkumar, Bren Professor at Caltech and Director of ML Research at NVIDIA. Discover principled approaches enabling zero-shot generalization beyond the training domain, including neural operators that provide 4-5 orders of magnitude speedups over numerical weather models and other scientific simulations. Learn how these innovations capture multi-scale processes by mapping between function spaces, with applications in weather and climate modeling, deep earth modeling, and more. Gain insights from Anandkumar's extensive experience and accolades in the field of AI, including her work on unsupervised AI, optimization, and tensor methods. This webinar is part of the DDPS series, offering valuable knowledge for those interested in the intersection of machine learning and scientific computing.
Overview
Syllabus
DDPS | ML for Solving PDEs: Neural Operators on Function Spaces by Anima Anandkumar
Taught by
Inside Livermore Lab