Performing Incremental Bayesian Inference by Dynamic Model Counting

AbstractThe ability to update the structure of a Bayesian network when new data becomes available is crucial for building adaptive systems. Recent work by Sang, Beame, and Kautz (AAAI 2005) demonstrates that the well-known Davis-Putnam procedure combined with a dynamic decomposition and caching technique is an effective method for exact inference in Bayesian networks with high density and width. In this paper, we define dynamic model counting and extend the dynamic decomposition and caching technique to multiple runs on a series of problems with similar structure. This allows us to perform Bayesian inference incrementally as the structure of the network changes. Experimental results show that our approach yields significant improvements over the previous model counting approaches on multiple challenging Bayesian network instances.

Download publication

Related Resources

See what’s new.



Stable Fluids

Building animation tools for fluid-like motions is an important and…



StyleCam: Interactive Stylized 3D Navigation using Integrated Spatial & Temporal Controls

We describe a new type of graphical user interface widget, known as a…



Crowdsourced Fabrication

In recent years, extensive research in the HCI literature has explored…



ChronoFab: Fabricating Motion

We present ChronoFab, a 3D modeling tool to craft motion sculptures,…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us