Skip to content

Experimental implementation of model tree dynamic Bayesian networks, mtDBN in short

License

Notifications You must be signed in to change notification settings

ComputationalIntelligenceGroup/mtDBN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

61 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

mtDBN

Experimental implementation of model tree dynamic Bayesian networks, mtDBN in short

This repository will serve as an initial implementation of the mtDBN model prior to being introduced into the dbnR package. Some of the objectives regarding this model are:

  • Test the improvements of the mtDBN model versus a regular DBN model
  • Test different kinds of splitting criteria for the tree model
  • Test multivariate trees versus univariate
  • Test the possibility of a forest model tree
  • Implement the mtDBN model as an R6 independent module in order to be able to easily introduce it into dbnR
  • Test the convergence of the PSOHO algorithm. It seems to range from pretty amazing networks to ones with abysmal forecasting performance

About

Experimental implementation of model tree dynamic Bayesian networks, mtDBN in short

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • R 100.0%