Modeling and Simulation Group Meeting

Scientific Machine Learning or Physics-Informed Machine Learning is a fusion of AI with physical, mathematical, and domain knowledge, and is at the forefront of tackling challenging forward and inverse problems involving PDEs.

In this session, we will delve into the transformative potential of physics-based, AI-driven techniques for PDEs, like Physics-Informed Neural Networks (PINNs), which integrate physical laws directly into neural network training, Fourier Neural Operator (FNO), which leverages Fourier transforms for resolution-invariant operator learning, and finally Physics-Informed Neural Operator (PINO), which combines the strength of PINNs and FNO. Practical demonstrations on implementing and comparing these methodologies in MATLAB will provide attendees with hands-on insights and tools for their research and projects. Join us as we explore this cutting-edge intersection of AI and PDEs, uncovering new possibilities and applications in science and engineering. 

Highlights include:

1. Physics Informed Neural Networks (PINNs) with Deep Learning Toolbox, and optionally Symbolic Math Toolbox and PDE Toolbox
2. Fourier Neural Operator with Deep Learning Toolbox
3. Physics-Informed Neural Operator with Deep Learning Toolbox

We will also share what it is like to work at the MathWorks, career opportunities, and how you can apply.