C. Coelho, M. F. P. Costa, and L.L. Ferrás, "The role of adaptive activation functions in Fractional Physics-Informed Neural Networks" in Proceedings of the International Conference of Numerical Analysis and Applied Mathematics (ICNAAM-2022) (AIP Conference Proceedings, accepted)
This library provides a Jupyter Notebook to replicate the experiments done in the paper "The role of adaptive activation functions in Fractional Physics-Informed Neural Networks", see [paper].
Note that this repository has a copy (not the latest) of the official DeepXDE library [1] with some modified portions of code: added code to print the values of the adaptive variables after training is completed, the number n in 'LAAF-n' was converted to be the initialization of the adaptive variables.
- Clone/Download the complete repository;
- Open the jupyter notebook inside.
If you found this resource useful in your research, please consider citing.
@inproceedings{,
title={The role of adaptive activation functions in Fractional Physics-Informed Neural Networks},
author={Coelho, C. and Costa, M. F. P. and Ferrás, L. L.},
booktitle={},
pages={},
year={2022},
organization={Proceedings of the International Conference of Numerical Analysis and Applied Mathematics (ICNAAM-2022) (AIP
Conference Proceedings, accepted)}
}