BNet.News
In This Issue: March/April 2006 
•   BN Model Presentation at SPIE's Defense & Security Symposium
•   BNet.Builder User Tip: Multiple Networks
•   BNet.EngineKit User Tip: CPT Operations
•   REMINDER: Upcoming UAI 2006 Conference
•   Publicize Your Belief Network Success Story
BN Model Presentation at SPIE's Defense & Security Symposium
Charles River Analytics scientists are presenting a paper outlining an iterative process for adapting and tuning BN models at the SPIE Defense & Security Symposium that will take place from April 17-21, 2006, in Orlando, Florida. The conference is an international symposium for researchers of sensors and sensor processing algorithms and is annually attended by several thousand researchers in industry, government, and academia.

Senior Vice President of Operations and Principal Scientist, Paul Gonsalves, and Senior Software Engineer, Catherine Call, are presenting the paper “Belief Network-based Situation Assessment for Air Operations Centers.”

To view the abstract of the paper, or to request a copy of the paper, click here.

REMINDER: Upcoming UAI 2006 Conference
The 22nd Conference on Uncertainty in Artificial Intelligence (UAI 2006) will take place from July 13th - July 16th, 2006, at the Massachusetts Institute of Technology in Cambridge, Massachusetts.

Scientists from Charles River Analytics will be presenting papers and will be available to answer questions about BNet.Builder and BNet.EngineKit.

For more information on the conference, click here.

BNet.Builder User Tip: Multiple Networks
When you open multiple Bayesian network files, each network is placed in its own tab in the main part of the application window. By default you can only view a single network at a time. However, if you drag one of the tabs to the right or bottom side of the window, you can view multiple networks at the same time. You can also right-click on a tab for more options.

BNet.EngineKit User Tip: CPT Operations
Each node has a Conditional Probability Table (CPT) represented by the Cpt class. This tip describes three useful operations you can perform on a Cpt object.
- Normalize: you can use the normalize() or normalizeAll() methods to make the rows in the CPT add up to one
- Uniform: you can use the uniform() or uniformAll() methods to set rows in the CPT to a uniform distribution
- Randomize: you can use the randomizeAll() method to set all of the CPT entries to random values

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

  Unsubscribe | Update Profile | Confirm | Complain | Forward