no code implementations • 22 Mar 2023 • Yanxia Qian, Yongchao Zhang, Yunqing Huang, Suchuan Dong
Our analyses show that, with feed-forward neural networks having two hidden layers and the $\tanh$ activation function, the PINN approximation errors for the solution field, its time derivative and its gradient field can be effectively bounded by the training loss and the number of training data points (quadrature points).
no code implementations • 12 Oct 2022 • Dan Wei, Tiejun Zhou, Yunqing Huang, Kai Jiang
The neural network model consists of two parts, a classifier and Structure-Parameter-Mapping (SPM) subnets.