“Use of Physics Based AI for Simulation and Modeling in Era of Digital Twins” by Cherukuri – ACM SIGGRAPH HISTORY ARCHIVES

“Use of Physics Based AI for Simulation and Modeling in Era of Digital Twins” by Cherukuri

  • ©

Conference:


Type(s):


Title:

    Use of Physics Based AI for Simulation and Modeling in Era of Digital Twins

Presenter(s)/Author(s):


Moderator(s):



Abstract:


    If you always wanted to have a magic framework under your hands that allows you to easily blend physics, as expressed by governing partial differential equations, boundary conditions, and training data to build high-fidelity, parameterized, surrogate deep learning models, applicable to solve problems across domains, then this course is definitely not to miss. The course will introduce you to the Modulus platform that abstracts the complexity of setting up a scalable training pipeline, so you can leverage your domain expertise to map problems to an AI model’s training and develop better neural network architectures. The platform offers a variety of approaches for training physics-based neural network models, from purely physics-driven models with physics-informed neural networks (PINNs) to physics-based, data-driven architectures such as neural operators. You will learn how to apply it to simulate use cases applicable across science and engineering domains, and graphics. You will be able to put development of your digital twins that include physics simulations to the next level. Many use cases will show you how widely same framework can be applied.


ACM Digital Library Publication:



Overview Page:



Submit a story:

If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org