The Physics-based Deep Learning Book, written by the Thuerey Group at the Technical University of Munich (TU Munich) (team of 20 people), is available online for free. The book "contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations. As much as possible, all topics come with hands-on code examples in the form of Jupyter notebooks to quickly get started. Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty modeling. We live in exciting times: these methods have a huge potential to fundamentally change what computer simulations can achieve."

Topics include "How to train networks to infer a fluid flow around shapes like airfoils, and estimate the uncertainty of the prediction", "How to use model equations as residuals to train networks that represent solutions, and how to improve upon these residual constraints by using differentiable simulations", and "How to more tightly interact with a full simulator for inverse problems".

The Physics-based Deep Learning Book

#solidstatelife #ai #aieducation #physics