Deep Ensembles

Researchers proposed Physics-Informed Conformal Prediction (PI-CP), a framework that embeds PDE residuals into the nonconformity score of split conformal prediction to give neural operators distributi…

A new study from researchers using NVIDIA PhysicsNeMo finds that Monte Carlo Dropout with concrete dropout achieves well-calibrated uncertainty estimates at a fraction of the computational cost of Dee…

A new Uncertainty-Aware Physics-Informed Neural Network (PINN) framework overcomes "Physics Shock" — catastrophic gradient divergence caused by enforcing rigid flood equations onto noisy satellite rad…