In this chapter we introduce causal networks, which are the basic graphical feature for (almost) everything in this book. We give rules for reasoning about relevance in causal networks; is knowledge of A relevant for my belief about B? These sections deal with reasoning under uncertainty in general. Next, Bayesian networks are defined as causal networks with the strength of the causal links represented as conditional probabilities. Finally, the chain rule for Bayesian networks is presented. The chain rule is the property that makes Bayesian networks a very powerful tool for representing domains with inherent uncertainty. The sections on Bayesian networks assume knowledge of probability calculus as laid out in Sections 1.1–1.4.


Conditional Probability Bayesian Network Directed Acyclic Graph Chain Rule Probability Table 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science +Business Media, LLC 2007

Personalised recommendations