keras-adf 19.1.0

Assumed Density Filtering (ADF) Probabilistic Networks

keras-adf provides implementations for probabilistic Tensorflow/Keras neural network layers, which are based on assumed density filtering. Assumed density filtering (ADF) is a general concept from Bayesian inference, but in the case of feed-forward neural networks that we consider here it is a way to approximately propagate a random distribution through the neural network.

The layers in this package have the same names and arguments as their corresponding Keras version. We use Gaussian distributions for our ADF approximations, which are described by their means and (co-)variances. So unlike the standard Keras layers, each keras-adf layer takes two inputs and produces two outputs (one for the means and one for the (co-)variances).

keras-adf layers can be used exactly like the corresponding Keras layers within a Keras model. However, as mentioned above, ADF layers take two inputs and produce two outputs instead of one, so it is not possible to simply mix ADF and standard layers within the same model.

from tensorflow.keras import Input, Model
from kerasadf.layers import Dense

in_mean = Input((10,))
in_var = Input((10,))
out_mean, out_var  = Dense(10, activation="relu")([in_mean, in_var])
model = Model([in_mean, in_var], [out_mean, out_var])

The Overview and Examples sections of our documentation provide more realistic and complete examples.

Project Information

keras-adf is released under the MIT license, its documentation lives at Read the Docs, the code on GitHub, and the latest release can be found on PyPI. It’s tested on Python 2.7 and 3.4+.

If you’d like to contribute to keras-adf you’re most welcome. We have written a short guide to help you get you started!

Further Reading

Additional information on the algorithmic aspects of keras-adf can be found in the following works:

• Jochen Gast, Stefan Roth, “Lightweight Probabilistic Deep Networks”, 2018

• Jan Macdonald, Stephan Wäldchen, Sascha Hauch, Gitta Kutyniok, “A Rate-Distortion Framework for Explaining Neural Network Decisions”, 2019

Acknowledgments

During the setup of this project we were heavily influenced and inspired by the works of Hynek Schlawack and in particular his attrs package and blog posts on testing and packaing and deploying to PyPI. Thank you for sharing your experiences and insights.