cherakhan/b-pinns

Pytorch implementation of Bayesian physics-informed neural networks

B-PINNs (Bayesian Physics-Informed Neural Networks)

This is the pytorch implementation of B-PINNs with Hamiltonian monte carlo algorithm.

B-PINN에 관한 설명은 제 블로그에 있습니다.

Used libraries

• pytorch 1.6.0
• numpy 1.19.1
• hamiltorch
• IDE: Visual studio code

Original work

@article{yang2020b,
  title={B-pinns: Bayesian physics-informed neural networks for forward and inverse pde problems with noisy data},
  author={Yang, Liu and Meng, Xuhui and Karniadakis, George Em},
  journal={arXiv preprint arXiv:2003.06097},
  year={2020}
}