bbhamux

Name	bbhamux JSON
Version	0.2.0 JSON
	download
home_page
Summary	Minimal library to construct Hierarchical Associative Memories
upload_time	2023-12-31 00:23:34
maintainer
docs_url	None
author	Ben Hoover
requires_python	>=3.10,<4.0
license	Apache 2.0
keywords
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # Barebones-HAMUX
> [HAMUX](https://github.com/bhoov/hamux) built using [equinox](https://github.com/patrick-kidger/equinox), minimal implementation. A temporary solution as HAMUX is being rebuilt.

Build any hopfield network using energy fundamentals. See the original [HAMUX documentation](https://bhoov.com/hamux/) for explanation.

## Install: File copy

All logic is in one file: `hamux.py`. Please copy this file into whatever project you are working on, and modify as needed. You will need to manually install dependencies:

```
pip install equinox jax
pip install pytest # for tests
```

Install correct version of `jaxlib` for your hardware (e.g., to run on GPUs).

Run `demo.ipynb` for an example training on MNIST. *Works best with GPU*

## Install: Pip



## Tests

All basic tests for this package are in `test.py`.

```
pytest test.py
```

## Citation

If this repository is useful for this work, please cite the following:

```
@inproceedings{
hoover2022universal,
title={A Universal Abstraction for Hierarchical Hopfield Networks},
author={Benjamin Hoover and Duen Horng Chau and Hendrik Strobelt and Dmitry Krotov},
booktitle={The Symbiosis of Deep Learning and Differential Equations II},
year={2022},
url={https://openreview.net/forum?id=SAv3nhzNWhw}
}
```
            

Raw data

            {
    "_id": null,
    "home_page": "",
    "name": "bbhamux",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.10,<4.0",
    "maintainer_email": "",
    "keywords": "",
    "author": "Ben Hoover",
    "author_email": "benhoover34@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/90/31/1c98c3038983a6666bd435b36fa98dfe6072b207f2373c4ed5d169d1c594/bbhamux-0.2.0.tar.gz",
    "platform": null,
    "description": "# Barebones-HAMUX\n> [HAMUX](https://github.com/bhoov/hamux) built using [equinox](https://github.com/patrick-kidger/equinox), minimal implementation. A temporary solution as HAMUX is being rebuilt.\n\nBuild any hopfield network using energy fundamentals. See the original [HAMUX documentation](https://bhoov.com/hamux/) for explanation.\n\n## Install: File copy\n\nAll logic is in one file: `hamux.py`. Please copy this file into whatever project you are working on, and modify as needed. You will need to manually install dependencies:\n\n```\npip install equinox jax\npip install pytest # for tests\n```\n\nInstall correct version of `jaxlib` for your hardware (e.g., to run on GPUs).\n\nRun `demo.ipynb` for an example training on MNIST. *Works best with GPU*\n\n## Install: Pip\n\n\n\n## Tests\n\nAll basic tests for this package are in `test.py`.\n\n```\npytest test.py\n```\n\n## Citation\n\nIf this repository is useful for this work, please cite the following:\n\n```\n@inproceedings{\nhoover2022universal,\ntitle={A Universal Abstraction for Hierarchical Hopfield Networks},\nauthor={Benjamin Hoover and Duen Horng Chau and Hendrik Strobelt and Dmitry Krotov},\nbooktitle={The Symbiosis of Deep Learning and Differential Equations II},\nyear={2022},\nurl={https://openreview.net/forum?id=SAv3nhzNWhw}\n}\n```",
    "bugtrack_url": null,
    "license": "Apache 2.0",
    "summary": "Minimal library to construct Hierarchical Associative Memories",
    "version": "0.2.0",
    "project_urls": null,
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "9bc1587f8be2be601720150c928ed70ae703a4f43cc6dadb7bad29a25bfcde86",
                "md5": "1ba363c98a03be65e33af0713b8db8b4",
                "sha256": "87753996081c0f0d51ae5e6d9269fbcc37ad1ae14de410879b4a65a2c306cde1"
            },
            "downloads": -1,
            "filename": "bbhamux-0.2.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "1ba363c98a03be65e33af0713b8db8b4",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.10,<4.0",
            "size": 5320,
            "upload_time": "2023-12-31T00:23:32",
            "upload_time_iso_8601": "2023-12-31T00:23:32.256248Z",
            "url": "https://files.pythonhosted.org/packages/9b/c1/587f8be2be601720150c928ed70ae703a4f43cc6dadb7bad29a25bfcde86/bbhamux-0.2.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "90311c98c3038983a6666bd435b36fa98dfe6072b207f2373c4ed5d169d1c594",
                "md5": "fb061cc9e3999c2a648cc04b1c5cc4b7",
                "sha256": "ace733398527b55ef8838131cae7a3ee663eca6883f60ad2842ac1bbb55518c8"
            },
            "downloads": -1,
            "filename": "bbhamux-0.2.0.tar.gz",
            "has_sig": false,
            "md5_digest": "fb061cc9e3999c2a648cc04b1c5cc4b7",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.10,<4.0",
            "size": 5028,
            "upload_time": "2023-12-31T00:23:34",
            "upload_time_iso_8601": "2023-12-31T00:23:34.314999Z",
            "url": "https://files.pythonhosted.org/packages/90/31/1c98c3038983a6666bd435b36fa98dfe6072b207f2373c4ed5d169d1c594/bbhamux-0.2.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-12-31 00:23:34",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "bbhamux"
}