tiny-bnn

A tiny Bayesian neural network using Monte Carlo variational inference, implemented in PyTorch. You can find more fleshed out implementations by Javier Antoran or Hoki Kim.

Install

Dependencies can be installed with

pip install -r requirements.txt

For managing Python projects, Pipenv or Anaconda can be useful.

Run

python run_bnn_demo.py -v

License

MIT license

Cite

@misc{tiny-bnn,
    title={Tiny BNN},
    author={Wright, Oren},
    booktitle={GitHub},
    year={2024},
    url = {https://github.com/omwright/tiny-bnn}
}