BNet.News May/June 2007

		BNet™.News

In This Issue:

May/June 2007

•	5th Bayesian Modeling Applications Workshop

•	BNet™.EngineKit User Tip: Evidence

•	Visit Our Publication Pages

•	View Back Issues of BNet™.News

•	BNet™.Builder User Tip: Evidence

•	Publicize Your Belief Network Success Story

5th Bayesian Modeling Applications Workshop

VANCOUVER, BC, CANADA -- The 5th Bayesian Modeling Applications Workshop will be held on July 19, 2007, in conjunction with the 23rd Conference on Uncertainty in Artificial Intelligence. The theme for this year's workshop is Bayesian Model Views.

Scientists from Charles River Analytics will be presenting a paper on "User-Centered Methods for Rapid Creation and Validation of Bayesian Belief Networks." They will also be available to discuss BNet™ products, including BNet™.Builder and BNet™.EngineKit.

For more information, click here.

Visit Our Publication Pages

Visit the Charles River Analytics Web site to view a list of our publications, including those referencing BNet™.Builder, BNet™.EngineKit, and Bayesian Belief Networks. You can view abstracts of many papers and request the full PDF.

To visit our publication pages, click here.

BNet™.Builder User Tip: Evidence

BNet™.Builder provides easy ways to work with evidence directly on the nodes in the network. Once you expand the evidence user interface on a node (by clicking the "Show evidence" button), you can click the "Hard evidence" button for a particular state. This sets its evidence to 100% and sets evidence for all other states to 0%. You can also drag the "soft evidence" sliders to represent uncertainty in the evidence, as well as type numerical evidence into the text fields.

To remove evidence from a node, click its "Retract evidence" button, found in the bottom-right corner of the node. To remove all evidence from a network, click the "Retract all evidence" button on the tool bar.

To learn more about BNet.Builder, click here.

BNet™.EngineKit User Tip: Evidence

The BNet™.EngineKit API provides several methods for working with evidence. You can set the evidence for a specific state using the DiscreteNode.setEvidence (String, double) method (the evidence on all other states will stay the same as before). You can set evidence for all states of a node at once using the DiscreteNode.setEvidence (double[]) method. Note that in all of these methods, evidence is in the range [0.0, 1.0].

To obtain the evidence for a specific state, use the DiscreteNode.getEvidence(String) method. To obtain the evidence for all states of a node, use the DiscreteNode.getEvidence() method.

You can remove the evidence from a node with the DiscreteNode.removeEvidence() method and you can remove evidence from all nodes in a network using the BayesianNetwork.clearEvidence() method.

To learn more about Engine.Kit, click here.

View Back Issues of BNet™.News

We have back issues of BNet™.News posted on our Web site. If you're a new subscriber or are looking for more articles and tips, come visit our Web site.

To visit the BNet.News archive, click here.

Publicize Your Belief Network Success Story


Want to show off your applications of belief networks to others using them in their research? Send us your success stories. We would like to include at least one in each edition of BNet.News. To send us your story, please contact lcordeiro@cra.com or zcox@cra.com.

BNet™.News is published by Charles River Analytics™, the company that brings you BNet.Builder™ and BNet.EngineKit™. View our Privacy Policy