Introduction to Physics-Informed Neural Networks

This 3-day block course covers the basics of Physics-Informed Neural Networks (PINNs). You'll learn how to combine deep learning with physical laws, specifically by incorporating differential equations into the training process. The goal is to create models that are physically accurate and work well even when you have a small amount of data. We spend the 3 days in a mixture of lecture, programming guided by jupyther notebooks and free programming tasks.

Prerequisites: 
Needed: Mathematics of Artificial Intelligence, basics of (partial) differential equations, basic Python skills. 
Advantageous: Knowledge from the Machine Learning Lecture.