Hello
I saw in the genie smile support that it deals with hybrid bayesian networks which contains continuous and discrete nodes and I built one, however I can't apply the EM algorithm for learning the parameters and do I have to do the discritization before applying the EM algorithm?
question
-
- Site Admin
- Posts: 431
- Joined: Tue Dec 11, 2007 4:24 pm
Re: question
Hi Nira,
Yes, this is correct. You will need to discretize the continuous variables in your data set (please make sure that they match the states in the network!). SMILE's implementation of the EM algorithm will work for mixture of discrete and continuous variables.
I hope this helps,
Marek
Yes, this is correct. You will need to discretize the continuous variables in your data set (please make sure that they match the states in the network!). SMILE's implementation of the EM algorithm will work for mixture of discrete and continuous variables.
I hope this helps,
Marek