tmflow

Name	tmflow JSON
Version	0.4.0 JSON
	download
home_page	https://github.com/PNN-Lab/tmflow
Summary	Taylor map flow is a package for a 'flowly' construction and learning of polynomial neural networks (PNN) for time-evolving process prediction
upload_time	2023-01-26 19:03:30
maintainer
docs_url	None
author	PNN Lab
requires_python	>=3.7, <4
license
keywords	pnn taylor ode tensorflow
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            Taylor map flow is a package for a 'flowly' construction and learning of polynomial neural networks (PNN) for time-evolving process prediction.

Based on the input time-series data, it provides:
  - (construct) a module to construct ordinary differential equations (ODEs) in the polynomial form
  - (map) a module to construct a matrix Taylor map for ODEs
  - (learn) a TensorFlow-based module to build and train a polynomial neural network (PNN).
Taylor map matrices can be used as PNN initial weights.

PNN built in this flow way is strongly connected with ordinary differential equations.
This combination reveals the data-underlying deterministic process without manual equation derivation 
and allows treating cases even when only small datasets or partial measurements are available. 
The proposed hybrid models provide explainable and interpretable results to leverage optimal control applications.

'Construct', 'map', and 'learn' modules can be used sequentially or independently from each other.

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/PNN-Lab/tmflow",
    "name": "tmflow",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.7, <4",
    "maintainer_email": "",
    "keywords": "PNN,Taylor,ODE,TensorFlow",
    "author": "PNN Lab",
    "author_email": "golovkina.a@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/45/7e/caff123278e771f340b9eb1fb31d749464c792490f24ea3ea802bea9edf2/tmflow-0.4.0.tar.gz",
    "platform": null,
    "description": "Taylor map flow is a package for a 'flowly' construction and learning of polynomial neural networks (PNN) for time-evolving process prediction.\r\n\r\nBased on the input time-series data, it provides:\r\n  - (construct) a module to construct ordinary differential equations (ODEs) in the polynomial form\r\n  - (map) a module to construct a matrix Taylor map for ODEs\r\n  - (learn) a TensorFlow-based module to build and train a polynomial neural network (PNN).\r\nTaylor map matrices can be used as PNN initial weights.\r\n\r\nPNN built in this flow way is strongly connected with ordinary differential equations.\r\nThis combination reveals the data-underlying deterministic process without manual equation derivation \r\nand allows treating cases even when only small datasets or partial measurements are available. \r\nThe proposed hybrid models provide explainable and interpretable results to leverage optimal control applications.\r\n\r\n'Construct', 'map', and 'learn' modules can be used sequentially or independently from each other.\r\n",
    "bugtrack_url": null,
    "license": "",
    "summary": "Taylor map flow is a package for a 'flowly' construction and learning of polynomial neural networks (PNN) for time-evolving process prediction",
    "version": "0.4.0",
    "split_keywords": [
        "pnn",
        "taylor",
        "ode",
        "tensorflow"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "9fc1a8fc5ff597a684cde26b63e1f450586f94ac8a7c339240091f4b78b284a9",
                "md5": "41829c8a4860326277b3742597d2d4bf",
                "sha256": "7bc2a314ea1e163695604d9664c3d308d90fb8ecf9ebfea9b83a93b7211788ac"
            },
            "downloads": -1,
            "filename": "tmflow-0.4.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "41829c8a4860326277b3742597d2d4bf",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.7, <4",
            "size": 22989,
            "upload_time": "2023-01-26T19:03:29",
            "upload_time_iso_8601": "2023-01-26T19:03:29.005188Z",
            "url": "https://files.pythonhosted.org/packages/9f/c1/a8fc5ff597a684cde26b63e1f450586f94ac8a7c339240091f4b78b284a9/tmflow-0.4.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "457ecaff123278e771f340b9eb1fb31d749464c792490f24ea3ea802bea9edf2",
                "md5": "fdb181cd78a781b372e04a6ec8c25a69",
                "sha256": "9b61ef8cbeee405389eb2767a09f8bb05f928806ff02edbde4f384637f00e145"
            },
            "downloads": -1,
            "filename": "tmflow-0.4.0.tar.gz",
            "has_sig": false,
            "md5_digest": "fdb181cd78a781b372e04a6ec8c25a69",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.7, <4",
            "size": 18520,
            "upload_time": "2023-01-26T19:03:30",
            "upload_time_iso_8601": "2023-01-26T19:03:30.650567Z",
            "url": "https://files.pythonhosted.org/packages/45/7e/caff123278e771f340b9eb1fb31d749464c792490f24ea3ea802bea9edf2/tmflow-0.4.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-01-26 19:03:30",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "github_user": "PNN-Lab",
    "github_project": "tmflow",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": false,
    "requirements": [],
    "lcname": "tmflow"
}