Search found 1255 matches

by shooltz[BayesFusion]
Tue Jul 28, 2020 8:35 am
Forum: SMILE
Topic: How log likelihood value is calculated in EM?
Replies: 6
Views: 70

Re: How log likelihood value is calculated in EM?

log p(x)=log (product of cliques/product of sepsets)? It's more complicated algorithm. We run relevance decomposition which may create a forest of junction trees (the same approach is used for the main exact inference algorithm). See this post for the explanation of the chain rule algorithm and P(e...
by shooltz[BayesFusion]
Tue Jul 28, 2020 8:14 am
Forum: SMILE
Topic: How log likelihood value is calculated in EM?
Replies: 6
Views: 70

Re: How log likelihood value is calculated in EM?

The primary algorithm for calculating the probability of evidence is based on the junction tree cliques. If the junction tree cannot be created due to memory constraints, the algorithm switches to chain rule (slower, but potentially less memory-intensive).
by shooltz[BayesFusion]
Fri Jul 24, 2020 9:11 am
Forum: GeNIe
Topic: About Parameter Learning
Replies: 5
Views: 111

Re: About Parameter Learning

An update: the automatic matching between integer indices (1,2,...) and the corresponding state names (Xyz1, Xyz2, Xyz3...) has been added to GeNIe. We plan to release the next version of the program later this summer.
by shooltz[BayesFusion]
Thu Jul 23, 2020 4:08 pm
Forum: GeNIe
Topic: About Parameter Learning
Replies: 5
Views: 111

Re: About Parameter Learning

The problem probably is related to the automatic matching between data columns and network nodes. Your data file contains numeric indices. During structure learning these indices are converted into string outcome identifiers. The PC/EM does it internally and there's no issue. Later on, when you run ...
by shooltz[BayesFusion]
Thu Jul 23, 2020 3:17 pm
Forum: GeNIe
Topic: About Parameter Learning
Replies: 5
Views: 111

Re: About Parameter Learning

Please post your data file and the network (after PC, before EM).
by shooltz[BayesFusion]
Thu Jul 23, 2020 1:39 pm
Forum: SMILE
Topic: pysmile k-fold CV
Replies: 5
Views: 2555

Re: pysmile k-fold CV

Can you share your "validator test.xdsl" file so we can reproduce the problem?
by shooltz[BayesFusion]
Mon Jul 20, 2020 9:26 pm
Forum: SMILE
Topic: pysmile k-fold CV
Replies: 5
Views: 2555

Re: pysmile k-fold CV

SMILE does not support validation (including k-fold) in DBNs. You need to unroll your network and run k-fold on the non-DBN model.
by shooltz[BayesFusion]
Fri Jul 17, 2020 11:21 pm
Forum: SMILE
Topic: I can not import pysmile in my mac.
Replies: 7
Views: 289

Re: I can not import pysmile in my mac.

Note that you can use parameter learning (EM algorithm) with the DBN. Create the structure first (including the temporal arcs), then run the parameter learning and your CPTs will be set based on the data.
by shooltz[BayesFusion]
Fri Jul 03, 2020 11:11 am
Forum: GeNIe
Topic: Unable to open .xdsl files with new GeNIe version
Replies: 2
Views: 182

Re: Unable to open .xdsl files with new GeNIe version

It seems that QGeNIe (which opens .qdsl file) took over the .xdsl extension in Windows registry - note that the icon for your networks is green/yellow/red instead of blue/red/green. It is not an expected behavior and we can't reproduce it. Can you uninstall GeNIe using Windows Add/Remove programs fu...
by shooltz[BayesFusion]
Mon Jun 08, 2020 8:39 pm
Forum: SMILE
Topic: When to run update_beliefs()
Replies: 1
Views: 151

Re: When to run update_beliefs()

You need to call update_beliefs when you have set the evidence and want to calculate and retrieve the calculated posterior probabilities. In your case, for each of the records in the test file you should remove the evidence, set new evidence with multiple calls to set_evidence, then call update_beli...
by shooltz[BayesFusion]
Mon Jun 08, 2020 8:34 pm
Forum: GeNIe
Topic: data type in GeNIe
Replies: 3
Views: 902

Re: data type in GeNIe

Your the HomeLocation variables are considered to be continuous, because the number of distinct values is greater than 20. To make sure GeNIe treats these variables as discrete, increase the 'Discrete threshold' parameter in the 'Learn New Network' window. Note that structure learning for dynamic ne...
by shooltz[BayesFusion]
Wed Jun 03, 2020 10:37 pm
Forum: SMILE
Topic: Enable diagnosis for nodes using pysmile wrapper
Replies: 3
Views: 956

Re: Enable diagnosis for nodes using pysmile wrapper

2. Is it possible to change the font type or size through PySmile wrapper? 3. Are there methods to convert the graph to a bar view or an icon view? Unfortunately, this functionality is not available from PySMILE. We will write a sample Python program using PySMILE's diagnostic functionality and pos...
by shooltz[BayesFusion]
Wed Jun 03, 2020 10:35 pm
Forum: GeNIe
Topic: data type in GeNIe
Replies: 3
Views: 902

Re: data type in GeNIe

such as I use 0,1,2,3,4,5,6,7,8,9 to represent age (0,10],(10,20], (20,30],...,(90,>90] in .csv file, then I input this csv file into GeNIe to make "learn structure" and "learn network'. I notice the dynamic bayesian network you provide on the website that we can use string to represent our value l...
by shooltz[BayesFusion]
Wed Jun 03, 2020 10:22 pm
Forum: GeNIe
Topic: GeNIe 2.5 released, includes QGeNIe now
Replies: 2
Views: 2200

Re: GeNIe 2.5 released, includes QGeNIe now

Version 2.5 is backwards compatible with 2.4. Your xdsl files won't be affected.
by shooltz[BayesFusion]
Wed May 13, 2020 1:27 pm
Forum: SMILE
Topic: Update error
Replies: 19
Views: 6817

Re: Update error

I used this method and the error still persisted. Are you sure you got the same error when inference algorithm was set to EPIS? BTW, Network.SampleCount defaults to 10000 and can be made much larger. Increasing the sample count does not require more memory, but it makes the inference run longer and...