Metadata-Version: 2.1
Name: autobnn
Version: 0.0.1.dev0
Summary: Package for training Gaussian process-like Bayesian Neural Networks with composite structure.
Home-page: https://github.com/tensorflow/probability/tree/main/spinoffs/autobnn
Author: Google LLC
Author-email: no-reply@google.com
License: Apache 2.0
Keywords: tensorflow jax probability statistics bayesian machine learning
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.6
Description-Content-Type: text/markdown

# 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`.
