It is shown that the weight matrices of a Physics-informed neural network (PINN)-based deep learning application to a rarefied gas dynamics problem described by the Boltzmann equation bear no evident link to the mathematical structure of the physical problem. Instead, the weights appear close to Gaussian distributed random matrices. Although significantly more work is needed to support a robust assessment in this direction, these results suggest that deep-learning and the numerical solution of the Boltzmann equation represent two equivalent, but largely distinct paths to the same physical knowledge. If so, Explainable AI might be an unrealistic target and possibly even an ill-posed one.
View on arXiv@article{tucny2025_2505.04627,
title={ Is the end of Insight in Sight ? },
author={ Jean-Michel Tucny and Mihir Durve and Sauro Succi },
journal={arXiv preprint arXiv:2505.04627},
year={ 2025 }
}