pclib

Name	pclib JSON
Version	2.0.0b2 JSON
	download
home_page
Summary	A torch-like package for building Predictive Coding Neural Networks.
upload_time	2024-03-06 11:29:50
maintainer
docs_url	None
author	Joe Griffith
requires_python
license
keywords	python neural networks deep learning predictive coding
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            
# PCLib





PCLib is a python package with a torch-like API for building and training Predictive Coding Networks.<br> 

Documentation can be found [here](https://joeagriffith.github.io/pclib/).



The package includes a fully-connected layer implementation, as well as a convolutional one. Both are customisable and can be used together or separately for building neural networks.



The package also includes a helper class for constructing fully-connected PCNs. This class has been designed to be extremely customiseable such that the network it builds can be used in a wide range of tasks: supervised/unsupervised, classic/inverted, etc. There is also a CNN class, however it is not customisable in shape. For more detailed explanations, please see the documentation.



## Installation

```

pip install pclib

```



## Example usage



In the examples folder you will find two different classification tasks which demonstrate the usage of this package.

            

Raw data

            {
    "_id": null,
    "home_page": "",
    "name": "pclib",
    "maintainer": "",
    "docs_url": null,
    "requires_python": "",
    "maintainer_email": "",
    "keywords": "python,neural networks,deep learning,predictive coding",
    "author": "Joe Griffith",
    "author_email": "joeagriffith@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/c4/36/15268248a01bd8e0f0cea5f25e10dbbd8dee9b7fbb0e760cb430cd6cf980/pclib-2.0.0b2.tar.gz",
    "platform": null,
    "description": "\r\n# PCLib\r\n\r\n\r\n\r\n\r\n\r\nPCLib is a python package with a torch-like API for building and training Predictive Coding Networks.<br> \r\n\r\nDocumentation can be found [here](https://joeagriffith.github.io/pclib/).\r\n\r\n\r\n\r\nThe package includes a fully-connected layer implementation, as well as a convolutional one. Both are customisable and can be used together or separately for building neural networks.\r\n\r\n\r\n\r\nThe package also includes a helper class for constructing fully-connected PCNs. This class has been designed to be extremely customiseable such that the network it builds can be used in a wide range of tasks: supervised/unsupervised, classic/inverted, etc. There is also a CNN class, however it is not customisable in shape. For more detailed explanations, please see the documentation.\r\n\r\n\r\n\r\n## Installation\r\n\r\n```\r\n\r\npip install pclib\r\n\r\n```\r\n\r\n\r\n\r\n## Example usage\r\n\r\n\r\n\r\nIn the examples folder you will find two different classification tasks which demonstrate the usage of this package.\r\n",
    "bugtrack_url": null,
    "license": "",
    "summary": "A torch-like package for building Predictive Coding Neural Networks.",
    "version": "2.0.0b2",
    "project_urls": null,
    "split_keywords": [
        "python",
        "neural networks",
        "deep learning",
        "predictive coding"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "eda0f920a9fe4faded3f1e84926668a5dce6fbc805ed297df5dc0eb180a5d7dc",
                "md5": "efa21aa31a93d0ae7553982a506dbd61",
                "sha256": "20e56091de68320b38a25c42cf5ee50e8466627bbd9043c23b50b361598aaaf8"
            },
            "downloads": -1,
            "filename": "pclib-2.0.0b2-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "efa21aa31a93d0ae7553982a506dbd61",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 42074,
            "upload_time": "2024-03-06T11:29:48",
            "upload_time_iso_8601": "2024-03-06T11:29:48.797162Z",
            "url": "https://files.pythonhosted.org/packages/ed/a0/f920a9fe4faded3f1e84926668a5dce6fbc805ed297df5dc0eb180a5d7dc/pclib-2.0.0b2-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "c43615268248a01bd8e0f0cea5f25e10dbbd8dee9b7fbb0e760cb430cd6cf980",
                "md5": "826a97490cd5be4527acc004b236bd4f",
                "sha256": "18ab74bfe6bd967772d77df3a3d0ea1a19daf623b2a9e1293747bd6375fba530"
            },
            "downloads": -1,
            "filename": "pclib-2.0.0b2.tar.gz",
            "has_sig": false,
            "md5_digest": "826a97490cd5be4527acc004b236bd4f",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 22670,
            "upload_time": "2024-03-06T11:29:50",
            "upload_time_iso_8601": "2024-03-06T11:29:50.539919Z",
            "url": "https://files.pythonhosted.org/packages/c4/36/15268248a01bd8e0f0cea5f25e10dbbd8dee9b7fbb0e760cb430cd6cf980/pclib-2.0.0b2.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-03-06 11:29:50",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "pclib"
}