B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
Liu Yang,Xuhui Meng,G. Karniadakis
2020 · DOI: 10.1016/j.jcp.2020.109913
Journal of Computational Physics · 引用 916 次
TLDR
Compared with PINNs, B-PINNs obtain more accurate predictions in scenarios with large noise due to their capability of avoiding overfitting and dropout employed in PINNs can hardly provide accurate predictions with reasonable uncertainty.