Search found 1417 matches

by shooltz[BayesFusion]
Thu May 21, 2009 5:05 pm
Forum: SMILE
Topic: Lauritzen algorithm?
Replies: 6
Views: 6832

ermutarra wrote:I'm not quite sure why you mean when you ask me to post the model
Model == network.

Did you use DSL_naiveBayes::Learn or created the arcs yourself, then ran DSL_em::Learn?
by shooltz[BayesFusion]
Thu May 21, 2009 12:06 pm
Forum: SMILE
Topic: Lauritzen algorithm?
Replies: 6
Views: 6832

Yes, the data is complete. It is a naive bayes classifier. The "G" node is the parent and the "D", "T", and "B" nodes are the children. I just want to clarify that DSL_ALG_BN_LAURITZEN is the identifier you can pass to DSL_network::SetDefaultBNAlgorithm, whic...
by shooltz[BayesFusion]
Wed May 20, 2009 11:22 pm
Forum: SMILE
Topic: Discretizer & Missing values
Replies: 1
Views: 3247

Re: Discretizer & Missing values

But now the method GetVariableData it's not available anymore. Which one should I use if I dont know before reading the kind of data that is coming? GetVariableData was replaced by GetIntData/GetFloatData. To check the type of the dataset column use IsDiscrete method. Another question is regarding ...
by shooltz[BayesFusion]
Wed May 20, 2009 11:01 am
Forum: SMILE
Topic: How do I access the values of the prior distribution?
Replies: 8
Views: 7410

The method I was looking for to know which state the probability corresponds to is theNames->Subscript(j) You can use (*theNames)[j] as well. Or use the reference (not pointer) to DSL_idArray: const DSL_idArray &theNames = *(theNet.GetNode(disthandle)->Definition()->GetOutcomesNames()); cout <<...
by shooltz[BayesFusion]
Wed May 20, 2009 10:42 am
Forum: GeNIe
Topic: problems with parameter learning with EM
Replies: 14
Views: 13088

Re: glad to hear

is there a time frame for the next release? Is it possible to get a preview? We'll be testing modified EM for couple of days. If it works OK we'll release GeNIe or at least notify you and provide link to preview version. As for the crashes - the software will crash when the input network has a node...
by shooltz[BayesFusion]
Wed May 20, 2009 10:13 am
Forum: SMILE
Topic: How do I access the values of the prior distribution?
Replies: 8
Views: 7410

The code I have at the moment is: probmatrix = theNet.GetNode(disthandle)->Definition()->GetMatrix(); int count = (probmatrix->GetSize())/NUM_GAITS; int n=0; double probs[NUM_GAITS][count]; I don't think this will compile. You'll need constant expression as array dimension; the 'count' variable is ...
by shooltz[BayesFusion]
Tue May 19, 2009 10:09 pm
Forum: GeNIe
Topic: problems with parameter learning with EM
Replies: 14
Views: 13088

Re: not randomizing the parameters

I will also mention that after a couple of dozen training sessions Genei tends to become unstable, and I see problems in image rendering and a significant tendency to crash, mostly if I try to close the program. Does this happen with small model you've attached in one of previous posts, or the larg...
by shooltz[BayesFusion]
Tue May 19, 2009 9:56 pm
Forum: GeNIe
Topic: Comparing the structure of 2 BNs
Replies: 1
Views: 3056

Re: Comparing the structure of 2 BNs

Can someone help me with this or provide a reference on a freely available tool or scripts for this type of analysis? I don't know about any existing tool/script for such task. You'd have to write such program yourself in C++, Java or .NET. I can help with any specific questions asked on this forum.
by shooltz[BayesFusion]
Mon May 18, 2009 6:36 pm
Forum: GeNIe
Topic: problems with parameter learning with EM
Replies: 14
Views: 13088

Re: some more information

ninio wrote:i'm using 2.0.3259.0, and the program tends to crash after several iterations of training.
Did you try the most recent build (2.0.3393.0)?
by shooltz[BayesFusion]
Mon May 18, 2009 3:53 pm
Forum: SMILE
Topic: Unobserved state?
Replies: 1
Views: 2791

Re: Unobserved state?

ermutarra wrote:Why is this happening? Can Smilearn not deal with variables that take only one value?
The 'unobserved state' is the way for SMILEarn to deal with data column containing only one value. SMILE's discrete nodes can have two or more outcomes and SMILearn must follow that constraint.
by shooltz[BayesFusion]
Mon May 18, 2009 1:30 pm
Forum: SMILE
Topic: Genie for Linux?
Replies: 1
Views: 3143

Re: Genie for Linux?

ermutarra wrote:I was wondering if you have a version of Genie for Linux??
No, your best bet is try to run GeNIe under WINE emulation layer.
by shooltz[BayesFusion]
Mon May 18, 2009 1:26 pm
Forum: SMILE
Topic: Nodes ordering
Replies: 2
Views: 3298

Re: Nodes ordering

Have a look at DSL_network::SimpleGraphLayout.
by shooltz[BayesFusion]
Thu May 07, 2009 10:51 pm
Forum: SMILE
Topic: More questions about DSL_dataset's ReadFile
Replies: 7
Views: 7097

Ok, I answer myself :) I've made the following function: But if you want to use entry in the dataset as a parameter when calling SetEvidence, you should do the lookup in the other direction: 1) get the integer value from the dataset 2) use that value as an index to obtain the string from stateNames...
by shooltz[BayesFusion]
Thu May 07, 2009 10:43 pm
Forum: SMILE
Topic: More questions about DSL_dataset's ReadFile
Replies: 7
Views: 7097

Hi, If I've the following file: NO YES YES NO And I make read file, the state 0 will be NO and YES will be state 1, but if you make in different order this will change. Just to clarify things, the order should not change. If dataset column contains non-numbers, they will be sorted alphabetically in...
by shooltz[BayesFusion]
Tue May 05, 2009 12:09 pm
Forum: SMILE
Topic: API Documentation for Dynamic BNs
Replies: 4
Views: 8675

Draft DBN docs

*** Using DBN features in SMILE *** 1) Basic scenario - setting temporal evidence, performing inference in dynamic network, reading the beliefs If the network has already the required structure and parameters (for example, was modeled in GeNIe and loaded from .xdsl file), then it's enough to call D...