Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint
Share this Page URL
Help

Chapter 4: Learning Bayesian Networks > 4.6 Software Packages for Learning

4.6 Software Packages for Learning

Based on considerations such as those illustrated in Section 4.4.1, Spirtes et al. [1993, 2000] developed an algorithm which finds the DAG faithful to P from the conditional independencies in P when there is a DAG faithful to P. Spirtes et al. [1993, 2000] further developed an algorithm which learns a DAG in which P is embedded faithfully from the conditional independencies in P when such a DAG exists. These algorithms have been implemented in the Tetrad software package [Scheines et al., 1994], which can be downloaded for free from the following site:

http://www.phil.cmu.edu/projects/tetrad/.

In 1997 Meek developed a heuristic search algorithm called Greedy Equivalent Search (GES) which has the following property: if there were a DAG faithful to P, the limit, as the size of the data set approaches infinity, of the probability of finding a DAG faithful to P is equal to 1. The Tetrad software package also has a module which uses that algorithm along with the Bayesian information criterion (BIC) to learn a Bayesian network from data.


  

You are currently reading a PREVIEW of this book.

                                                                                                                    

Get instant access to over $1 million worth of books and videos.

  

Start a Free 10-Day Trial


  
  • Safari Books Online
  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint