01

Last Updated: 10 months ago2024-05-12 ; Contributors: AhmedThahir, web-flow

Typical Scientific Tasks

PINN

Physics-Informed Neural Networks

Digital Twin

Physics’ Properties Preferred in Machine Learning

• Interpretability

• Generalizability

• Parsimony/Simplicity

• Symmetries/Conservations

• Invariance: $(f \circ g)(x) = f(x)$

• Equivariance: $(f \circ g)(x) = (g \circ f)(x)$

where

• $f$ is deep learning model
• $g$ is a transformation such as rotation

Comments