Physics-informed machine learning (physics-ML) leverages knowledge of the physical world to train AI models, which can be used to emulate real-world systems as surrogates or digital twins. Some applications include predicting extreme weather, modeling full-waveform inversion, simulating turbulent flow over a car, and modeling proteins.

Dr. George Karniadakis, a professor of applied mathematics and engineering at Brown University, will speak about why his team designed the Science and Engineering Teaching Kit for the NVIDIA Deep Learning Institute (DLI). He’ll share his perspective on the current state and the progress of the physics-ML domain and how educators can prepare their students by incorporating AI topics into their curriculums.

Join this webinar to learn how NVIDIA has collaborated with pioneers at the intersection of science, engineering, and AI to develop resources to help professionals in these fields. This includes the first-ever deep learning for Science and Engineering Teaching Kit for educators and self-paced learning modules for practitioners. It uses the NVIDIA Modulus physics-ML platform to help professionals explore and experiment with these new techniques and algorithms with ease.

• Learn about physics-ML applications in science and engineering

• Explore the resources available to educate engineers and scientists, including the DLI Teaching Kit and new algorithms and techniques for physics-ML

• Get an overview of NVIDIA Modulus, the physics-ML platform for engineers and scientists

Content

content goes here