Deep fuzzy physics-informed neural networks for forward and inverse PDE problems

Wenyuan Wu, Siyuan Duan, Yuan Sun, Yang Yu, Dong Liu, Dezhong Peng

Abstract: Highlights•FPINNs is proposed to incorporate fuzzy learning for reducing uncertainty in PINNs.•Fuzzy rules and Gaussian membership functions is used to improve solution accuracy.•FPINNs outperform existing methods in solving both forward and inverse PDEs.