This is the code for the paper "Higher-order-ReLU-KANs (HRKANs) for solving physics-informed neural networks (PINNs) more accurately, robustly and faster".

1. The files torch_relu.py, torch_hrkan.py and the folder kan contain the python implementation of ReLU-KAN, HRKAN and KAN respectively. Both torch_relu.py and the folder kan are downloaded from corresponding github of their authors.

2. The two jupyter notebook file Poisson_equation.ipynb and Burgers_equation_with_viscosity.ipynb contain the codes for the two experiments in our paper.