Description:

The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilistic models, including Bayesian networks, Markov networks, dependency networks, sum-product networks, arithmetic circuits, and mixtures of trees.

Learning algorithms -- Structure learning for BNs, MNs, DNs, SPNs, and mixtures of trees; learning tractable BNs and MNs with ACs; MN weight learning

Inference algorithms -- Mean field, belief propagation, max-product, Gibbs sampling, iterated conditional modes, AC variable elimination, AC exact inference

Libra's strengths include structure learning, tractable models, and exploiting sparse factors.

Changes to previous version:

Version 1.1.2d (12/29/2015):

• Minor fixes to scripts
• Published in JMLR ML-OSS!

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Cygwin, Linux, Mac Os X

Data Formats: Ascii

Tags: Structure Learning, Approximate Inference, Bayesian Networks, Markov Random Fields, Dependency Networks, Arithmetic Circuits, Exact Inference, Markov Networks, Sum Product Networks

Archive: download here

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.