O'Reilly logo

Building Probabilistic Graphical Models with Python by Kiran R Karkera

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Constraint-based structure learning

In this approach, we start with a set of vertices that represent random variables in the data, and then we test for conditional dependence (and independence) in the data. The goal of this approach is to read the conditional dependence and independence of the data from the Bayesian network structure. The constraints are essentially tests of conditional independencies between the random variables.

The algorithm can be logically divided into three parts.

Part I

For each variable Xi, the algorithm attempts to find a subset of witness variables (say, X1 to Xn) in the presence of which Xi is independent of the other variables. However, examining all subsets of the random variables will require searching over an exponential ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required