2025/05/07 by Jean‐Michel Tucny, Tucny, Jean-Michel, Mihir Durve +3
Computer Science · Materials Science · Physics and Astronomy · #Artificial neural network #Cognition #Computational Physics (physics.comp-ph) #Data Analysis #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #FOS: Physical sciences #Ideal (ethics) #Interpretability #Machine Learning (cs.LG) #Machine Learning in Materials Science #Model Reduction and Neural Networks #Outcome (game theory) #Perspective (graphical) #Statistics and Probability (physics.data-an) #TRACE (psycholinguistics)
paper · pdf · doi:10.48550/arxiv.2505.04627
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/05/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The rise of deep learning challenges the longstanding scientific ideal of insight - the human capacity to understand phenomena by uncovering underlying mechanisms. In many modern applications, accurate predictions no longer require interpretable models, prompting debate about whether explainability is a realistic or even meaningful goal. From our perspective in physics, we examine this tension through a concrete case study: a physics-informed neural network (PINN) trained on a rarefied gas dynamics problem governed by the Boltzmann equation. Despite the system's clear structure and well-understood governing laws, the trained network's weights resemble Gaussian-distributed random matrices, with no evident trace of the physical principles involved. This suggests that deep learning and traditional simulation may follow distinct cognitive paths to the same outcome - one grounded in mechanistic insight, the other in statistical interpolation. Our findings raise critical questions about the limits of explainable AI and whether interpretability can - or should-remain a universal standard in artificial reasoning.