## Neural Tangent Kernel for `scikit-learn` Gaussian Processes
    [](#citation)
**scikit-ntk** is implementation of the neural tangent kernel (NTK) for the `scikit-learn` machine learning library as part of "An Empirical Analysis of the Laplace and Neural Tangent Kernels" master's thesis (found at [http://hdl.handle.net/20.500.12680/d504rr81v](http://hdl.handle.net/20.500.12680/d504rr81v) and [https://arxiv.org/abs/2208.03761](https://arxiv.org/abs/2208.03761)). This library is meant to directly integrate with [`sklearn.gaussian_process`](https://scikit-learn.org/stable/modules/classes.html#module-sklearn.gaussian_process) module. This implementation of the NTK can be used in combination with other kernels to train and predict with Gaussian process regressors and classifiers.
## Installation
### Dependencies
scikit-ntk requires:
* Python (>=3.8)
* scikit-learn (>=1.0.1)
### User installation
In terminal using `pip` run:
```bash
pip install scikit-ntk
```
### Usage
Usage is described in [`examples/usage.py`](https://github.com/392781/scikit-ntk/blob/master/example/usage.py); however, to get started simply import the `NeuralTangentKernel` class:
```py
from skntk import NeuralTangentKernel as NTK
kernel_ntk = NTK(D=3, bias=0.01, bias_bounds=(1e-6, 1e6))
```
Once declared, usage is the same as other `scikit-learn` kernels.
## Building
Python Poetry (>=1.2) is required if you wish to build `scikit-ntk` from source. In order to build follow these steps:
1. Clone the repository
```bash
git clone git@github.com:392781/scikit-ntk.git
```
2. Enable a Poetry virtual environment
```bash
poetry shell
```
3. Build and install
```bash
poetry build
poetry install --with dev
```
## Citation
If you use scikit-ntk in your scientific work, please use the following citation alongside the scikit-learn citations found at [https://scikit-learn.org/stable/about.html#citing-scikit-learn](https://scikit-learn.org/stable/about.html#citing-scikit-learn):
```
@mastersthesis{lencevicius2022laplacentk,
author = "Ronaldas Paulius Lencevicius",
title = "An Empirical Analysis of the Laplace and Neural Tangent Kernels",
school = "California State Polytechnic University, Pomona",
year = "2022",
month = "August",
note = {\url{http://hdl.handle.net/20.500.12680/d504rr81v}}
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/392781/scikit-ntk",
"name": "scikit-ntk",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.14,>=3.8",
"maintainer_email": null,
"keywords": "sckit-learn, sklearn",
"author": "Ronaldas P Lencevi\u010dius",
"author_email": "contact@ronaldas.dev",
"download_url": "https://files.pythonhosted.org/packages/51/96/b2a7af9daa4f2c986d2e97a001125572ebee0591d605038298ad7307283c/scikit_ntk-1.2.1.tar.gz",
"platform": null,
"description": "## Neural Tangent Kernel for `scikit-learn` Gaussian Processes\n\n    [](#citation)\n\n**scikit-ntk** is implementation of the neural tangent kernel (NTK) for the `scikit-learn` machine learning library as part of \"An Empirical Analysis of the Laplace and Neural Tangent Kernels\" master's thesis (found at [http://hdl.handle.net/20.500.12680/d504rr81v](http://hdl.handle.net/20.500.12680/d504rr81v) and [https://arxiv.org/abs/2208.03761](https://arxiv.org/abs/2208.03761)). This library is meant to directly integrate with [`sklearn.gaussian_process`](https://scikit-learn.org/stable/modules/classes.html#module-sklearn.gaussian_process) module. This implementation of the NTK can be used in combination with other kernels to train and predict with Gaussian process regressors and classifiers. \n\n## Installation\n\n### Dependencies\n\nscikit-ntk requires:\n* Python (>=3.8)\n* scikit-learn (>=1.0.1)\n\n\n### User installation\nIn terminal using `pip` run:\n\n```bash\npip install scikit-ntk\n```\n\n### Usage\nUsage is described in [`examples/usage.py`](https://github.com/392781/scikit-ntk/blob/master/example/usage.py); however, to get started simply import the `NeuralTangentKernel` class:\n\n```py\nfrom skntk import NeuralTangentKernel as NTK\n\nkernel_ntk = NTK(D=3, bias=0.01, bias_bounds=(1e-6, 1e6))\n```\nOnce declared, usage is the same as other `scikit-learn` kernels.\n\n## Building\nPython Poetry (>=1.2) is required if you wish to build `scikit-ntk` from source. In order to build follow these steps:\n\n1. Clone the repository\n```bash\ngit clone git@github.com:392781/scikit-ntk.git\n```\n2. Enable a Poetry virtual environment\n```bash\npoetry shell\n```\n3. Build and install\n```bash\npoetry build\npoetry install --with dev\n```\n\n## Citation\n\nIf you use scikit-ntk in your scientific work, please use the following citation alongside the scikit-learn citations found at [https://scikit-learn.org/stable/about.html#citing-scikit-learn](https://scikit-learn.org/stable/about.html#citing-scikit-learn):\n\n```\n@mastersthesis{lencevicius2022laplacentk,\n author = \"Ronaldas Paulius Lencevicius\",\n title = \"An Empirical Analysis of the Laplace and Neural Tangent Kernels\",\n school = \"California State Polytechnic University, Pomona\",\n year = \"2022\",\n month = \"August\",\n note = {\\url{http://hdl.handle.net/20.500.12680/d504rr81v}}\n}\n```\n",
"bugtrack_url": null,
"license": "BSD-3-Clause",
"summary": "Implementation of the neural tangent kernel for scikit-learn's Gaussian process module.",
"version": "1.2.1",
"project_urls": {
"Bug Tracker": "https://github.com/392781/scikit-ntk/issues",
"Homepage": "https://github.com/392781/scikit-ntk",
"Repository": "https://github.com/392781/scikit-ntk"
},
"split_keywords": [
"sckit-learn",
" sklearn"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f1a938204bed67b4d3d532d2270a12b1a0003506e72166229dc0f4b2bdce541f",
"md5": "29dc0fecc670117d25dc523b405d2d64",
"sha256": "953c5a2d32b5b549e7627a5f5dbceaa66d5a16498d736ddc2b678c384f28d3a6"
},
"downloads": -1,
"filename": "scikit_ntk-1.2.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "29dc0fecc670117d25dc523b405d2d64",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.14,>=3.8",
"size": 5246,
"upload_time": "2024-10-07T23:21:16",
"upload_time_iso_8601": "2024-10-07T23:21:16.537260Z",
"url": "https://files.pythonhosted.org/packages/f1/a9/38204bed67b4d3d532d2270a12b1a0003506e72166229dc0f4b2bdce541f/scikit_ntk-1.2.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "5196b2a7af9daa4f2c986d2e97a001125572ebee0591d605038298ad7307283c",
"md5": "e94c41cf9099001127719153297fb915",
"sha256": "8a1bd65d146b4121cd1c696b04b014821d8c2870c319f3d426efd77509e04085"
},
"downloads": -1,
"filename": "scikit_ntk-1.2.1.tar.gz",
"has_sig": false,
"md5_digest": "e94c41cf9099001127719153297fb915",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.14,>=3.8",
"size": 5172,
"upload_time": "2024-10-07T23:21:17",
"upload_time_iso_8601": "2024-10-07T23:21:17.428974Z",
"url": "https://files.pythonhosted.org/packages/51/96/b2a7af9daa4f2c986d2e97a001125572ebee0591d605038298ad7307283c/scikit_ntk-1.2.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-07 23:21:17",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "392781",
"github_project": "scikit-ntk",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "scikit-ntk"
}
JSON
