Machine Learning in Materials Processing & Characterization
Unit 9: Inverse Problems and Process Maps
FAU Erlangen-Nürnberg
Today’s Learning Journey:
The Solution: Using physics as a “regularizer” to guide the model toward valid solutions.
“Why hide knowledge from an algorithm when it would improve training?” Neuer, Michael et al., (2024)
GradientTape to compute the residuals.
© Philipp Pelz - Machine Learning in Materials Processing & Characterization