Learning Objectives:

• Understand why standard neural networks fail for physics problems
• Learn how to incorporate physics into neural network training
• Master automatic differentiation for computing derivatives
• Compare data-driven vs physics-informed approaches

This topic includes materials that are collected together in Jupyter notebooks that can be run to reproduce the results contained in the topic pages. Access to the notebooks is described in the Lab page at the end of this topic: Lab: PINNs, Poisson Problem, and Inverse Problems. If you would like to run the code in the notebooks as you work through the materials in this topic, consult that Lab page for information on how to proceed.