ConceptMathematics
Physics-informed neural networks
A machine learning approach that incorporates physical laws, such as PDEs, into the loss function to solve differential equations.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
3Each in their own terms, from the easiest level.
Costas Sarris
Neural networks trained to solve supervised learning tasks while respecting any given laws of physics described by general nonlinear partial differential equations.John M. Aiken
Physics-informed neural networks add known physical laws, such as projectile motion equations and drag forces, directly into the loss function used to train the machine learning model.
Connections
8The lectures that define it or assume it, and the concepts next to it.