Mizuka Komatsu: Application of differential elimination for Physics-Informed Neural Networks

Differential elimination refers to the elimination of specific variables and/or their derivatives from differential equations. It has gained recognition for its notable application in the model identifiability analysis while we explore further applications in this talk. In particular, we introduce the application of differential elimination for Physics-Informed Neural Networks (PINNs), which are types of deep neural networks integrating governing equations behind the data.