# DEGANN
[](https://github.com/Krekep/degann/actions/workflows/tests.yml)
[](https://github.com/Krekep/degann/blob/main/LICENSE)
[](https://pypi.org/project/degann/)
**DEGANN** is a library generating neural networks for approximating solutions to differential equations. As a backend for working with neural networks, tensorflow is used, but with the ability to expand with your own tools.
**Features**
- Generation of neural networks by parameters.
- Construction of tables with the numerical solution of ordinary differential equations of the first order
- Construction of tables with numerical solution of systems of ordinary differential equations of the first order
- Choosing the Best Neural Network from Several for Fixed Training Parameters
- Iterating over training parameters with choosing the best neural network for each set
- Export Neural Networks as a function in C++
- Export Neural Networks as a Parameter Set
- Import Neural Networks from a Parameter Set
- Building a dataset with complete training results for approximating the solution of a differential equation for each neural network that participated in training
- Advanced search for optimal topology using a language that describes the topology of a neural network
- Random search for optimal neural network topology
- Method for simulating annealing of optimal neural network topology
- Expert system for automatic selection of optimal parameters for algorithms for searching neural network topologies
## Install
### Manual
Download the repository as a zip archive, unpack and run the command from the root of the repository
```bash
pip install -r requirements.txt
```
This will download and install all the dependencies for the project, then you can use the source code of the library (e.g. create project nearby to the `degann` folder)
### Via pip
Use command
```bash
pip install degann
```
Now you can use the `degann` package
Raw data
{
"_id": null,
"home_page": "https://github.com/Krekep/degann",
"name": "degann",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "python, ode, differential equation, neural network",
"author": "Pavel Alimov",
"author_email": "<pashaalimov@gmail.com>",
"download_url": null,
"platform": null,
"description": "# DEGANN\r\n\r\n[](https://github.com/Krekep/degann/actions/workflows/tests.yml)\r\n[](https://github.com/Krekep/degann/blob/main/LICENSE)\r\n[](https://pypi.org/project/degann/)\r\n\r\n**DEGANN** is a library generating neural networks for approximating solutions to differential equations. As a backend for working with neural networks, tensorflow is used, but with the ability to expand with your own tools.\r\n\r\n**Features**\r\n- Generation of neural networks by parameters.\r\n- Construction of tables with the numerical solution of ordinary differential equations of the first order\r\n- Construction of tables with numerical solution of systems of ordinary differential equations of the first order\r\n- Choosing the Best Neural Network from Several for Fixed Training Parameters\r\n- Iterating over training parameters with choosing the best neural network for each set\r\n- Export Neural Networks as a function in C++\r\n- Export Neural Networks as a Parameter Set\r\n- Import Neural Networks from a Parameter Set\r\n- Building a dataset with complete training results for approximating the solution of a differential equation for each neural network that participated in training\r\n- Advanced search for optimal topology using a language that describes the topology of a neural network\r\n- Random search for optimal neural network topology\r\n- Method for simulating annealing of optimal neural network topology\r\n- Expert system for automatic selection of optimal parameters for algorithms for searching neural network topologies\r\n\r\n## Install\r\n\r\n### Manual\r\nDownload the repository as a zip archive, unpack and run the command from the root of the repository\r\n```bash\r\npip install -r requirements.txt\r\n```\r\nThis will download and install all the dependencies for the project, then you can use the source code of the library (e.g. create project nearby to the `degann` folder)\r\n\r\n### Via pip\r\nUse command\r\n```bash\r\npip install degann\r\n```\r\nNow you can use the `degann` package\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Library for generating artificial neural networks for modeling the behavior of dynamic systems",
"version": "1.1.5",
"project_urls": {
"Homepage": "https://github.com/Krekep/degann"
},
"split_keywords": [
"python",
" ode",
" differential equation",
" neural network"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a3dc9ffc6d09b6b2675655598a17f437630dbc9a1d3abecdabb2d51f016820ad",
"md5": "966c73d0297380342259e3f84eef491f",
"sha256": "ccebe83a09900b9115e782be97071d6559107adac2a3b2850f5dfafd050f7e56"
},
"downloads": -1,
"filename": "degann-1.1.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "966c73d0297380342259e3f84eef491f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 43658,
"upload_time": "2024-05-31T08:36:28",
"upload_time_iso_8601": "2024-05-31T08:36:28.487699Z",
"url": "https://files.pythonhosted.org/packages/a3/dc/9ffc6d09b6b2675655598a17f437630dbc9a1d3abecdabb2d51f016820ad/degann-1.1.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-31 08:36:28",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Krekep",
"github_project": "degann",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "black",
"specs": [
[
"~=",
"23.3.0"
]
]
},
{
"name": "keras",
"specs": [
[
"~=",
"3.3.3"
]
]
},
{
"name": "matplotlib",
"specs": [
[
"~=",
"3.7.1"
]
]
},
{
"name": "numpy",
"specs": [
[
"~=",
"1.26.4"
]
]
},
{
"name": "pre-commit",
"specs": [
[
"~=",
"3.3.1"
]
]
},
{
"name": "pytest",
"specs": [
[
"~=",
"7.3.1"
]
]
},
{
"name": "scipy",
"specs": [
[
"~=",
"1.13.1"
]
]
},
{
"name": "tensorflow",
"specs": [
[
"~=",
"2.16.1"
]
]
}
],
"lcname": "degann"
}
JSON
