Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Attend this 80-minute seminar from the Data-Driven Physical Simulations (DDPS) series featuring ETH Zurich's Siddhartha Mishra exploring the intersection of artificial intelligence and physics simulations. Learn about the computational challenges of traditional numerical methods for Partial Differential Equations (PDEs) and discover how Machine Learning and AI-based neural PDE surrogates offer faster, more accurate alternatives. Explore the latest developments in Neural Operators, including convolution and attention-based architectures, and examine graph and transformer-based approaches for PDEs on arbitrary domains. Understand how conditional Diffusion models handle chaotic multiscale solutions and investigate the development of general-purpose Foundation models for PDEs to address sample complexity issues. Gain insights from a leading expert who directs the Computational and Applied Mathematics Laboratory at ETH Zurich and serves as Director of Computational Science Zurich, with applications spanning astrophysics, geophysics, climate science, engineering, and biology.
