IDI Bayesian Network Course – Next Course Oct. 13-15, 2020

IDI Bayesian Network Course – Next Course Oct. 13-15, 2020 2020-10-19T19:24:07+00:00
Download Flyer for October Course
Register Today for the October 13-15, 2020 Course!

Location: 1951 Kidwell Drive, Suite 750, Vienna, VA 22182
Time: 8:30 am to 4:30 pm

Course Description: 

The course focus is on constructing and analyzing Bayesian networks (BNs) in Netica – from simple models for learning the basics to more complex, real-world applications for learning advanced features. Through a hands-on learning process, students will have the opportunity to explore examples and work on networks from their own work places during class exercises.

The cost is $1950 which includes snacks each day. A discount of $200 for early registration by September 14th is available. We also offer a $200 discount for multiple persons from the same organization. Only one discount can be used.

A temporary student license for the Netica software will be provided. Students do not need to purchase Netica for the course. PLEASE bring your own laptop. The course is very hands-on.


Further Information:

Please keep an eye on this webpage for further information and updates. We can also teach this course at your site at another time. Email Dennis at with questions or suggestions.

Course Topics (order is subject to change):

Day 1

  • Introduction
  • Building a simple Bayesian network (BN) – drug testing
  • Just enough probability
  • A complete diagnostic BN – Liver diagnosis case study
  • Elicitation of BN structure and probabilities
  • Causal Models

Day 2

  • Troubleshooting systems – Netica car diagnosis example
  • Troubleshooting systems – Industrial system example
  • Learning probabilities for a BN from data
  • Student Workshop (opportunity to work on your own BN problem)
  • D-Separation and sensitivity to findings
  • Combining expert knowledge and data
  • BN Building Practicum
  • Learning structure for a BN from data

Day 3

  • Netica API
  • Student Workshop
  • Learning a BN with continuous variables
  • Introduction to GeoNetica™
  • Student Workshop
  • Dynamic Bayesian networks / Incorporation of evidence over time

Advanced topics available on a case-by-case basis

  • Continuous variables – Model aggregation example & discretization
  • Named probability distributions in Netica
  • Inference and basics of the propagation algorithm behind BNs
  • Bayesian network formulation practicum – build lots of BNs
  • Decision making in Netica using influence diagrams
  • Intro to integrating Netica with Excel
  • Using the Netica library in the ExtendSim discrete event simulation