2 papers
physics.flu-dyn2026
Stable and Interpretable Multi-Mode Rheological Universal Differential Equations (mmRUDEs) for Data-Driven Constitutive Modeling
Mohua Das, Nicholas King, Navid Azizan +1
The Rheological Universal Differential Equation (RUDE) framework embeds neural networks within a frame-indifferent tensorial constitutive backbone and so enables data-driven discov…
cs.LG2026
Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
Mohua Das, Pierfrancesco Beneventano, Shibshankar Dey +2
Randomly initialized neural networks induce a prior over functions, but the predictor used in practice is produced only after training. We ask how much of this initial bias survive…