Using the example program symbolic_regression.py as a reference: when the grid_size in build_splines_layers is set too large (e.g., 600), the A matrix in curve2coeff within layers.py results in NaN values, causing a calculation error. However, with the same grid_size value, the original efficient_kan can compute normally. I hope the author can address this issue in the next version.
Using the example program symbolic_regression.py as a reference: when the grid_size in build_splines_layers is set too large (e.g., 600), the A matrix in curve2coeff within layers.py results in NaN values, causing a calculation error. However, with the same grid_size value, the original efficient_kan can compute normally. I hope the author can address this issue in the next version.