275B Class Project: Empirical Evaluations of Some Benchmark Bayesian Networks
Authors: Igor Cadez, Hong Zhao, Stephen Bay, Scott Gafney, Dmitry Pavlov

This paper reports students' projects performed during the 275a class: "Network-based reasoning: belief networks", in the department of Information and Computer Science at UC-Irvine, taught by Rina Dechter. Students were required to select one problem from the Bayesian Repository Benchmarks and to run a comparative study of several known algorithms and report the results. This paper include five of the students' reports. The problems used are: Pigs, Diabetes, Insurance, HailFinder and ALARM.
  [ps] [pdf]