A derivative-fidelity failure mode in physics-informed neural networks: strengthened benchmark evidence from function-value training
Uncovering the hidden accuracy gap in PINNs where function fitting masks physical derivative errors.
Physics-informed neural networks (PINNs) use automatic differentiation to impose differential-equation residuals, but good agreement in function values does not necessarily imply accurate derivatives. This paper formulates derivative fidelity as a failure mode of PINNs and tests ...
ArXiv CS.LG
Source
Generated insight by OnAirToday AI
This research highlights a critical vulnerability in scientific machine learning where models achieve high accuracy on function values while failing to capture the underlying physical gradients. Addressing this derivative-fidelity gap is essential for ensuring the reliability of neural operators in high-stakes engineering and physical simulations.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.