Open access
Aug 2026
Variational Physics-Informed Neural Network with Functional Constraints Based on Operator Self-Adjointness
Experiments show that FC-VPINN achieves approximately one-order-of-magnitude lower prediction errors than the traditional PINN and reduces memory usage to 40% of that required by the baseline, demonstrating improved accuracy and computational efficiency in multidimensional problems.
Wenjie Zhang, Yu-Bo Li, Wei-Dong Cui et al.
· Chinese Physics B · 0 citations