Church

From Church Wiki

Church is a probabilistic programming language designed for expressive description of generative models (Goodman, Mansinghka, Roy, Bonawitz and Tenenbaum, 2008). Church is a derivative of the programming language Scheme with probabilistic semantics. This website serves as a portal to work related to Church, including a reference implementation and a repository of probabilistic models expressed in Church.

• Probabilistic Models of Cognition Tutorial (under construction)
• Papers using or studying the Church language.

Church Examples

Many probabilistic models are described as generative processes. Church is a formal language for describing generative processes. (The following examples give only Church code, see Getting Started with MIT-Church for how to run these from a Scheme script.)

• Estimating the parameters of a Gaussian
• Mixture models
• Ising models

The MIT-Church Implementation

The current implementation of Church (including the MCMC inference) is in alpha testing. If you are interested in helping to alpha test this implementation email Noah Goodman.

• Installation
• Getting Started with MIT-Church
• Documentation
• Bug reports and feature requests can be logged on the issue tracker.

It is also possible to use MIT-Church through the ChurchServ online interface, hosted by the Church Working Group at MIT. However limited computation is available through ChurchServ, so this should not be used for complex modeling or long jobs.

External Utilities

There are several ways to interface Church with external programs. A few useful things:

• Emacs
• Python
• R

Under Construction

• Cognitive Science models repository
• Churchserv Examples
• Benchmark Suite
• Key features of Church

If you would like to contribute to the site, please email Daniel Roy.