# AutoBNN
This library contains code to specify BNNs that correspond to various useful GP
kernels and assemble them into models using operators such as Addition,
Multiplication and Changepoint.
It is based on the ideas in the following papers:
* Lassi Meronen, Martin Trapp, Arno Solin. _Periodic Activation Functions
Induce Stationarity_. NeurIPS 2021.
* Tim Pearce, Russell Tsuchida, Mohamed Zaki, Alexandra Brintrup, Andy Neely.
_Expressive Priors in Bayesian Neural Networks: Kernel Combinations and
Periodic Functions_. UAI 2019.
* Feras A. Saad, Brian J. Patton, Matthew D. Hoffman, Rif A. Saurous,
Vikash K. Mansinghka. _Sequential Monte Carlo Learning for Time Series
Structure Discovery_. ICML 2023.
## Setup
AutoBNN has three additional dependencies beyond those used by the core
Tensorflow Probability package: flax, scipy and jaxtyping. These
can be installed by running `setup_autobnn.sh`.
Raw data
{
"_id": null,
"home_page": "https://github.com/tensorflow/probability/tree/main/spinoffs/autobnn",
"name": "autobnn",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": "tensorflow jax probability statistics bayesian machine learning",
"author": "Google LLC",
"author_email": "no-reply@google.com",
"download_url": "https://files.pythonhosted.org/packages/15/e0/bf807fac2bd5d6630947fd6590e50590a5c6d00761e6fec8e97f5d912701/autobnn-0.0.2.dev0.tar.gz",
"platform": null,
"description": "# AutoBNN\n\nThis library contains code to specify BNNs that correspond to various useful GP\nkernels and assemble them into models using operators such as Addition,\nMultiplication and Changepoint.\n\nIt is based on the ideas in the following papers:\n\n* Lassi Meronen, Martin Trapp, Arno Solin. _Periodic Activation Functions\nInduce Stationarity_. NeurIPS 2021.\n\n* Tim Pearce, Russell Tsuchida, Mohamed Zaki, Alexandra Brintrup, Andy Neely.\n_Expressive Priors in Bayesian Neural Networks: Kernel Combinations and\nPeriodic Functions_. UAI 2019.\n\n* Feras A. Saad, Brian J. Patton, Matthew D. Hoffman, Rif A. Saurous,\nVikash K. Mansinghka. _Sequential Monte Carlo Learning for Time Series\nStructure Discovery_. ICML 2023.\n\n\n## Setup\n\nAutoBNN has three additional dependencies beyond those used by the core\nTensorflow Probability package: flax, scipy and jaxtyping. These\ncan be installed by running `setup_autobnn.sh`.\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "Package for training Gaussian process-like Bayesian Neural Networks with composite structure.",
"version": "0.0.2.dev0",
"project_urls": {
"Homepage": "https://github.com/tensorflow/probability/tree/main/spinoffs/autobnn"
},
"split_keywords": [
"tensorflow",
"jax",
"probability",
"statistics",
"bayesian",
"machine",
"learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "15e0bf807fac2bd5d6630947fd6590e50590a5c6d00761e6fec8e97f5d912701",
"md5": "f85e3af935d6888dc294eb636b92605c",
"sha256": "8ca445c8d9c03cc4a9f54281dbeea561ae708fd1dcc37ebf1c7854fc78ab964b"
},
"downloads": -1,
"filename": "autobnn-0.0.2.dev0.tar.gz",
"has_sig": false,
"md5_digest": "f85e3af935d6888dc294eb636b92605c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 29372,
"upload_time": "2024-03-28T00:19:39",
"upload_time_iso_8601": "2024-03-28T00:19:39.230725Z",
"url": "https://files.pythonhosted.org/packages/15/e0/bf807fac2bd5d6630947fd6590e50590a5c6d00761e6fec8e97f5d912701/autobnn-0.0.2.dev0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-28 00:19:39",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "tensorflow",
"github_project": "probability",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "autobnn"
}
JSON
