Julia package for automatically generating Bayesian inference algorithms through message passing on Forney-style factor graphs.
Switch branches/tags
Clone or download
Latest commit e74870a Dec 5, 2018

README.md

ForneyLab.jl

Build Status

ForneyLab.jl is a Julia package for automatic generation of (Bayesian) inference algorithms. Given a probabilistic model, ForneyLab generates efficient Julia code for message-passing based inference. It uses the model structure to generate an algorithm that consists of a sequence of local computations on a Forney-style factor graph (FFG) representation of the model. For an excellent introduction to message passing and FFGs, see The Factor Graph Approach to Model-Based Signal Processing by Loeliger et al. (2007).

We designed ForneyLab with a focus on flexible and modular modeling of time-series data. ForneyLab enables a user to:

  • Conveniently specify a probabilistic model;
  • Automatically generate an efficient inference algorithm;
  • Compile the inference algorithm to executable Julia code.

The current version supports belief propagation (sum-product message passing), variational message passing and expectation propagation.

The ForneyLab project page provides more background on ForneyLab as well as pointers to related literature and talks. For a practical introduction, have a look at the demos.

Installation

Install ForneyLab through the Julia package manager:

] add ForneyLab

If you want to be able to use the graph visualization functions, you will also need to have GraphViz installed. On Linux, just use apt-get install graphviz or yum install graphviz. On Windows, run the installer and afterwards manually add the path of the GraphViz installation to the PATH system variable. On MacOS, use for example brew install graphviz. The dot command should work from the command line.

Some demos use the PyPlot plotting module. Install it using ] add PyPlot.

Optionally, use ] test ForneyLab to validate the installation by running the test suite.

Getting started

There are demos available to get you started. Additionally, the ForneyLab project page contains a talk and other resources that might be helpful.

License

(c) 2018 GN Store Nord A/S. Permission to use this software for any non-commercial purpose is granted. See LICENSE.md file for details.