Search found 18 matches
- Mon Mar 13, 2017 7:47 pm
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Re: Issues with node states flip in parameter learning output
Thank you so much, Marek! This helps a lot.
- Fri Mar 10, 2017 7:14 pm
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Re: Issues with node states flip in parameter learning output
Thank you so much!
- Fri Mar 10, 2017 7:05 am
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Re: Issues with node states flip in parameter learning output
I have tried but still could not fix the issues. I have attached a dataset, a network file, and the output (including log-likelihood value) I pulled out for two datasets. From the output, it is obvious that the order of p (state =0) and p(state=1) flip between different nodes and EM runs with differ...
- Thu Mar 09, 2017 8:03 pm
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Re: Issues with node states flip in parameter learning output
It's helpful to get your confirmation that the parameters are not updated. This seems to show me where I should go to find the problem. I will try myself first to see if it can be fixed...
Many thanks!
Many thanks!
- Thu Mar 09, 2017 7:11 pm
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Re: Issues with node states flip in parameter learning output
Using SetUniformParameters (true), all estimated parameters with regard to nodes A, B, C and D are .50.
It seems they are not updated by EM.
Also, in the code posted above, I remove that part below staticEM (). I think the problem should be in the EM part.
Thanks, again!
It seems they are not updated by EM.
Also, in the code posted above, I remove that part below staticEM (). I think the problem should be in the EM part.
Thanks, again!
- Thu Mar 09, 2017 6:54 pm
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Re: Issues with node states flip in parameter learning output
Thanks! Here is my code. My data was saved in C:\\Users\\b445h711\\Desktop\\c500\\data_l500.csv. It contains 10000 rows and 14850 columns, representing 495 datasets. In each dataset, there are 10000 rows (observations) and 30 columns representing 30 binary variables (1 = true,0=false). In the networ...
- Wed Mar 08, 2017 7:16 pm
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Re: Issues with node states flip in parameter learning output
Thank you so much for the reply. Could you give me any suggestions or hints to fix this problem with my code? I just want to make sure all parameters have a fixed position in the matrix/CP table so that I can know which is which when I extract them. And these positions will not change between runs w...
- Wed Mar 08, 2017 8:41 am
- Forum: SMILE
- Topic: Issues with node states flip in parameter learning output
- Replies: 14
- Views: 11866
Issues with node states flip in parameter learning output
Hello, I am doing a simulation study, in which I use static EM to estimate the parameters of a BN. I assume that in SMILE the CPs are saved into a matrix based on the rule introduced in the manual and following the same rule, I extract CPs using the codes as follows. However, I noticed that there se...
- Tue Mar 07, 2017 4:50 pm
- Forum: SMILE
- Topic: How to set maximum iterations and criterion for convergence in parameter learning
- Replies: 4
- Views: 4908
- Tue Mar 07, 2017 3:54 pm
- Forum: SMILE
- Topic: How to set maximum iterations and criterion for convergence in parameter learning
- Replies: 4
- Views: 4908
Re: How to set maximum iterations and criterion for convergence in parameter learning
So, at this point, the maximum number of iteration cannot be re-set either, right?
- Tue Mar 07, 2017 1:53 am
- Forum: SMILE
- Topic: How to set maximum iterations and criterion for convergence in parameter learning
- Replies: 4
- Views: 4908
How to set maximum iterations and criterion for convergence in parameter learning
Hello,
Does DSL provide any functions to set or change the maximum iterations and criterion for convergence in parameter learning using static EM? And what is the default setting for the maximum iteration in static EM?
Thank you,
Bo
Does DSL provide any functions to set or change the maximum iterations and criterion for convergence in parameter learning using static EM? And what is the default setting for the maximum iteration in static EM?
Thank you,
Bo
- Thu Dec 15, 2016 8:11 pm
- Forum: SMILE
- Topic: different conditional probabilities orders between EM runs in parameter learning
- Replies: 2
- Views: 3589
Re: different conditional probabilities orders between EM runs in parameter learning
Thank you so much! After fixing the random seed, everything looks good.
- Wed Dec 14, 2016 8:16 pm
- Forum: SMILE
- Topic: different conditional probabilities orders between EM runs in parameter learning
- Replies: 2
- Views: 3589
different conditional probabilities orders between EM runs in parameter learning
Hello, I generated a couple of data samples using a certain Bayesian network structure and settings for conditional probabilities. Then, with each sample of data, I performed parameter learning and extracted all estimated conditional probabilities. Using the code I attached, I noticed that the order...
- Mon Aug 29, 2016 9:54 pm
- Forum: SMILE
- Topic: More questions about Conditional Probabilities in Parameter Learning
- Replies: 3
- Views: 6735
Re: More questions about Conditional Probabilities in Parameter Learning
Yes, the order of conditional probabilities is changing between EM runs. Because I do not get the rule by which these probabilities are presented in the outcome, it's hard to tell which is which. Here is the code I used to create the network. There are 30 observed variables, x1.............x30, whic...
- Mon Aug 29, 2016 2:34 pm
- Forum: SMILE
- Topic: More questions about Conditional Probabilities in Parameter Learning
- Replies: 3
- Views: 6735
More questions about Conditional Probabilities in Parameter Learning
Hello, I encountered some troubles when I tried to extract the conditional probability. 1) I got a linear 4-node structure, where B is conditional on A, C is conditional on B, and D is conditional on C. However, when I checked the conditional probability matrix for node, there are 4 elements (there ...