# Neural network-based model approximation (nnbma)
[](https://badge.fury.io/py/nnbma)
[](https://ism-model-nn-approximation.readthedocs.io/en/latest/?badge=latest)
Neural network-based model approximation `nnbma` is a Python package that handle the creation and the training of neural networks to approximate numerical models.
In \[1\], it was designed and used to derive an approximation of the Meudon PDR code, a complex astrophysical numerical code.
## Installation
To build your own neural network for your numerical model, we recommend installing the package.
The package can be installed with `pip`:
```shell
pip install nnbma
```
To reproduce the results from \[1\], clone the repo with
```shell
git clone git@github.com:einigl/ism-model-nn-approximation.git
```
Alternatively, you can also download a zip file.
This package relies on _PyTorch_ to build neural networks.
It enables to evaluate any neural network, its gradient, and its Hessian matrix efficiently.
If you do not have a Python environment compatible with the above dependencies, we advise you to create a specific conda environment to use this code (<https://conda.io/projects/conda/en/latest/user-guide/>).
## References
\[1\] Palud, P. & Einig, L. & Le Petit, F. & Bron, E. & Chainais, P. & Chanussot, J. & Pety, J. & Thouvenin, P.-A. & Languignon, D. & Beslić, I. & G. Santa-Maria, M. & Orkisz, J.H. & Ségal, L. & Zakardjian, A. & Bardeau, S. & Gerin, M. & Goicoechea, J.R. & Gratier, P. & Guzman, V. (2023). Neural network-based emulation of interstellar medium models. Astronomy & Astrophysics. 10.1051/0004-6361/202347074.
Raw data
{
"_id": null,
"home_page": "https://github.com/einigl/ism-model-nn-approximation",
"name": "nnbma",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "machine learning, neural network",
"author": "Lucas Einig",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/4e/d9/267e9c49f6c585d12f2f220843f2e11a3aaa768d6d3f223b3e0a06ba929b/nnbma-1.0.2.tar.gz",
"platform": null,
"description": "# Neural network-based model approximation (nnbma)\n\n[](https://badge.fury.io/py/nnbma)\n[](https://ism-model-nn-approximation.readthedocs.io/en/latest/?badge=latest)\n\n\nNeural network-based model approximation `nnbma` is a Python package that handle the creation and the training of neural networks to approximate numerical models.\nIn \\[1\\], it was designed and used to derive an approximation of the Meudon PDR code, a complex astrophysical numerical code.\n\n## Installation\n\nTo build your own neural network for your numerical model, we recommend installing the package.\nThe package can be installed with `pip`:\n\n```shell\npip install nnbma\n```\n\nTo reproduce the results from \\[1\\], clone the repo with\n\n```shell\ngit clone git@github.com:einigl/ism-model-nn-approximation.git\n```\n\nAlternatively, you can also download a zip file.\n\nThis package relies on _PyTorch_ to build neural networks.\nIt enables to evaluate any neural network, its gradient, and its Hessian matrix efficiently.\n\nIf you do not have a Python environment compatible with the above dependencies, we advise you to create a specific conda environment to use this code (<https://conda.io/projects/conda/en/latest/user-guide/>).\n\n## References\n\n\\[1\\] Palud, P. & Einig, L. & Le Petit, F. & Bron, E. & Chainais, P. & Chanussot, J. & Pety, J. & Thouvenin, P.-A. & Languignon, D. & Besli\u0107, I. & G. Santa-Maria, M. & Orkisz, J.H. & S\u00e9gal, L. & Zakardjian, A. & Bardeau, S. & Gerin, M. & Goicoechea, J.R. & Gratier, P. & Guzman, V. (2023). Neural network-based emulation of interstellar medium models. Astronomy & Astrophysics. 10.1051/0004-6361/202347074.\n\n",
"bugtrack_url": null,
"license": null,
"summary": "Neural network-based model approximation (nnbma)",
"version": "1.0.2",
"project_urls": {
"Bug Tracker": "https://github.com/einigl/ism-model-nn-approximation/issues",
"Documentation": "https://ism-model-nn-approximation.readthedocs.io/en/latest/",
"Homepage": "https://github.com/einigl/ism-model-nn-approximation",
"Repository": "https://github.com/einigl/ism-model-nn-approximation"
},
"split_keywords": [
"machine learning",
" neural network"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8ec259e786bdccc5fc1963bd85a390fe4f57c6008d71721e35b4e16215d6d681",
"md5": "34382ce81c6b2c809b02e507d0cfb25b",
"sha256": "b2454637ce02c3ab41433e7c8b1eb3595982560b43f97f15724e3ba0957b1c5d"
},
"downloads": -1,
"filename": "nnbma-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "34382ce81c6b2c809b02e507d0cfb25b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 37818,
"upload_time": "2024-10-02T11:35:28",
"upload_time_iso_8601": "2024-10-02T11:35:28.358153Z",
"url": "https://files.pythonhosted.org/packages/8e/c2/59e786bdccc5fc1963bd85a390fe4f57c6008d71721e35b4e16215d6d681/nnbma-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "4ed9267e9c49f6c585d12f2f220843f2e11a3aaa768d6d3f223b3e0a06ba929b",
"md5": "9dea0bebf59aaed9f3c6c45bf3ee8e97",
"sha256": "118369ddd9fcf43f0c315166c5944c19dfb2779de5329eaf5a7cdcda1c83cac3"
},
"downloads": -1,
"filename": "nnbma-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "9dea0bebf59aaed9f3c6c45bf3ee8e97",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 28474,
"upload_time": "2024-10-02T11:35:29",
"upload_time_iso_8601": "2024-10-02T11:35:29.375989Z",
"url": "https://files.pythonhosted.org/packages/4e/d9/267e9c49f6c585d12f2f220843f2e11a3aaa768d6d3f223b3e0a06ba929b/nnbma-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-02 11:35:29",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "einigl",
"github_project": "ism-model-nn-approximation",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "nnbma"
}
JSON
