PiNNIEs is a Python package designed to solve mathematical problems that involve integral operators such as Fredholm, Volterra, or fractional derivatives using Physics-Informed Neural Networks (PINNs).
Note: This package is under heavy development and is not yet optimized for real-world problems.
The project is built on PyTorch for training PINNs. You can install pinnies via pip:
pip install pinniesTo see how to use the Pinnies package, please refer to the examples folder in the repository. The examples provide detailed usage instructions and showcase the capabilities of the package.
Pinnies is currently in the early stages of development. The focus is on establishing the core functionalities required for solving problems involving integral operators. As such, the package may not be fully optimized, and additional features and improvements are planned for future releases.
If you use pinnies in your research, please cite the following paper:
@misc{aghaei2024pinnies,
title={{PINNIES: An Efficient Physics-Informed Neural Network Framework to Integral Operator Problems}},
author={Afzal Aghaei, Alireza and Movahedian Moghaddam, Mahdi and Parand, Kourosh},
doi = {10.48550/ARXIV.2409.01899},
url = {https://arxiv.org/abs/2409.01899},
year = {2024},
publisher = {arXiv},
}This project is licensed under the MIT License - see the LICENSE file for details.
Contributions are welcome! If you have any suggestions, bug reports, or feature requests, please open an issue or submit a pull request.
For any inquiries or questions, please contact the lead author:
- Alireza Afzal Aghaei - alirezaafzalaghaei@gmail.com