Physics Informed Machine Learning with MATLAB
Overview
This webinar is aimed to introduce the concept and different methods of integrating known physical laws into AI-based methods such as Physics-Informed Neural Networks (PINNs), Fourier Neural Operator (FNO), and finally Physics-Informed Neural Operator (PINO). By incorporating additional information of known physical behaviors, the trained network can generate more accurate predictions outside of the given measurement data. Additionally, we will demonstrate practical examples on using PINN to solve a forward and inverse problems in MATLAB.
Highlights
- Learn about the concept of Physics Informed Neural Networks
- Explore the use of the method to solve Partial Differential Equations
- Learn how to set up and solve the problem in MATLAB
About the Presenters
Christoph Stockhammer joined MathWorks in 2012. His focus areas include mathematics, data analytics, machine and deep Learning, and the integration of MATLAB software components in other programming languages and environments. He holds a M.Sc. in mathematics with an emphasis on optimization from the Technical University of Munich.
Chyannie Fahdzyana is an Application Engineer at MathWorks Benelux, The Netherlands. Chyannie received her PhD degree in Mechanical Engineering from the Eindhoven University of Technology in 2021. At MathWorks, she focuses on topics related to Digital Twins, optimization, modelling and control, data analysis, and AI.
