Uncertainty Quantification in Neural Differential Equations
This work addresses the need for reliable deep learning models in differential equation applications, but it is incremental as it adapts existing methods.
The paper tackled the problem of uncertainty quantification in neural differential equation solvers by adapting existing UQ methods, showing results on four differential equation types.
Uncertainty quantification (UQ) helps to make trustworthy predictions based on collected observations and uncertain domain knowledge. With increased usage of deep learning in various applications, the need for efficient UQ methods that can make deep models more reliable has increased as well. Among applications that can benefit from effective handling of uncertainty are the deep learning based differential equation (DE) solvers. We adapt several state-of-the-art UQ methods to get the predictive uncertainty for DE solutions and show the results on four different DE types.