BayesFusion Support Forum

Can you post the actual network (not just the screenshot) here?

There are two parameters for controlling EM algorithm:

1) 'confidence level'. It's described in the dialog box shown after matching network and data and before running EM; see this thread for more information:

http://genie.sis.pitt.edu/forum/viewtopic.php?t=4

2) 'randomize initial parameters ...

What about using one of these sites where you type the search term and they return relevant links?

Check this and/or GeNIe's help file:

http://genie.sis.pitt.edu/wiki/GeNIe_Tu ... Parameters

The naive Bayes algorithm can't be applied in your case - it creates simple model with arcs directed from 'class node' into all other nodes. Since you're interested in structure where arcs go into specified node (Off_Alw_Fo), the PC algorithm should work. In fact, you've obtained the model which is ...

Would you please to provide library .NET compact framework? Already having a library for .NET framework, is it hard job to convert .NET framework to .NET compact framework?

I don't know - we don't have any experience with .NET CF. You're the first user asking for support on this platform. While ...

jam wrote:The parameter naive doing everything contrary to what we wish to undertake, and i do not understand why.

Can you post your data/learned network and explain what's the problem with the net?

It appears that there is a bug with decision nodes as parent of nature nodes in the Smile engine. Please import the following Netica file to see the bug.

The file loads OK with the following warning messages logged (despite the 'ERROR' prefix, they're just warnings):

(line 13) : ERROR ...

On the oder hand, , in the help of genie appears one thing, in my software appears otherwise, I would like to know why. Additions a document

The screenshot in help file shows old dialog, which had all parameters for all structure learning algorithms visible. They were just enabled/disabled ...

Is there a way to find network boundaries (i.e. maxX and maxY)?

Iterate over the nodes, retrieve the position of each node and create the union rectangle.

If you're using C++, then you could use DSL_network::SimpleGraphLayout after adding the nodes at any position. This would use parent ordering ...

jam wrote:I want to know that other options exist apart from the background knowledge and parameter naive to build my network without the Genie randomization

What do you mean by 'parameter naive'?

I'm not sure what exactly is your problem. Did you used automatic translator? If so, please ask somebody who knows English to translate for you.

I have tried to build a Bayesian network from a database, apparently genie takes the data and unites them at random

GeNIe certainly does not 'unite data at random'. All available data is read and used by learning algorithms.

The naive algorithm doesn't allow any background knowledge, but you can ...

andrew_ling wrote:Please import the following Netica file to see the bug.

There's no file attached to your post.

Can you perhaps elaborate on the circumstances under which this error is likely to occur?

(disclaimer: not a sampling expert here)

Most likely reason is that probability of the evidence you've set is very small. Did you increase the number of samples above the default value with Network ...