Hi,
The tornado diagram is only available in GeNIe, not in SMILE.
Best,
Martijn
Search found 76 matches
- Sun Mar 24, 2013 12:27 am
- Forum: SMILE
- Topic: Degree of Influence and Sensitivity Analysis
- Replies: 18
- Views: 23443
- Sat Mar 23, 2013 8:41 pm
- Forum: GeNIe
- Topic: DBN, inference algorithms and unrolling
- Replies: 33
- Views: 25296
Re: DBN, inference algorithms and unrolling
Hi,
Polytree is the algorithm proposed by Pearl:
Here's a reference:
Judea Pearl. (1986). Fusion, Propagation, and Structuring in Belief Networks. Artificial Intelligence, 29(3), 241-288
Pdf: http://www.ece.tamu.edu/~bjyoon/ecen689 ... l_1986.pdf
Polytree is the algorithm proposed by Pearl:
Here's a reference:
Judea Pearl. (1986). Fusion, Propagation, and Structuring in Belief Networks. Artificial Intelligence, 29(3), 241-288
Pdf: http://www.ece.tamu.edu/~bjyoon/ecen689 ... l_1986.pdf
- Thu Mar 14, 2013 2:39 pm
- Forum: SMILE
- Topic: SMILE with VS 2005 Runtime Error
- Replies: 3
- Views: 4239
Re: SMILE with VS 2005 Runtime Error
Hi Vikram,
Did you use the VS 2005 version of our library?
You can find it on our download page:
http://genie.sis.pitt.edu/index.php/downloads
Best,
Martijn
Did you use the VS 2005 version of our library?
You can find it on our download page:
http://genie.sis.pitt.edu/index.php/downloads
Best,
Martijn
- Sun Feb 17, 2013 6:01 pm
- Forum: SMILE
- Topic: How to read file from database?
- Replies: 7
- Views: 7010
Re: How to read file from database?
Hi, The SMILE library does not have the ability to read from a database directly. In general, you would have to implement that yourself (in your own code) and, using the SMILE library, construct the DSL_network object from what you have read from your database. Are you storing whole xdsl files in yo...
- Thu Feb 07, 2013 4:22 pm
- Forum: GeNIe
- Topic: Validating Network with GeNIe
- Replies: 8
- Views: 7618
Re: Validating Network with GeNIe
Hi Oscar, One more question. I don't quite understand what the difference is between having the DBN unrolled or not. Does it make any difference to the parameter learning process? No, it's just a matter of representation. A DBN is in fact just a normal Bayesian network, with some added symantics (we...
- Wed Feb 06, 2013 4:44 pm
- Forum: GeNIe
- Topic: Validating Network with GeNIe
- Replies: 8
- Views: 7618
Re: Validating Network with GeNIe
We have the Annealed MAP algorithm implemented which will find the most probable sequence of states, but it doesn't work directly on DBNs, i.e. with temperal plates. Currently it crashes. It will work when you unroll your network. You can find it under Network -> Annealed Map Right clicking on the n...
Re: EM Learn
Hi Oscar, I've tried to run EM myself on your data and network (which was attached to your previous post) and found a few thing you will have to fix. I wasn't successful running the SMILE code, and when trying to learn the parameters using GeNIe I found the following: 1. There's a mismatch between v...
Re: EM Learn
Hi Oscar, Since your network is a DBN, you may need a different approach to EM learning (Shooltz, does MatchNetwork work with DBNs already?) On our wiki we have two tutorials dealing with performing EM on DBNs: http://genie.sis.pitt.edu/wiki/SMILearn_Tutorial_6:_Learning_with_the_EM_Algorithm_(Dynam...
- Fri Dec 14, 2012 11:32 pm
- Forum: GeNIe
- Topic: How to replace all missing value at one time
- Replies: 1
- Views: 2570
Re: How to replace all missing value at one time
Hi YY,
As far as I can tell you can only replace missing values one column at a time.
Best,
Martijn
As far as I can tell you can only replace missing values one column at a time.
Best,
Martijn
- Fri Dec 14, 2012 11:22 pm
- Forum: GeNIe
- Topic: Posterior Updates after New Evidence
- Replies: 1
- Views: 2689
Re: Posterior Updates after New Evidence
Hi YY, You can update the network by pressing F5 (for updating once), or by pressing ctr-F5 (for continuously updating the network). For a more convenient view of all posteriors you can select all the nodes, press the right mouse button and go to view as-> Bar chart. This will show all nodes as bar ...
- Thu Aug 30, 2012 3:14 pm
- Forum: GeNIe
- Topic: Probabilities for several nodes
- Replies: 3
- Views: 4544
Re: Probabilities for several nodes
hi Suchard,
Yes, that's how it works.
Best,
Martijn
Yes, that's how it works.
Best,
Martijn
- Thu Aug 30, 2012 1:29 pm
- Forum: GeNIe
- Topic: Probabilities for several nodes
- Replies: 3
- Views: 4544
Re: Probabilities for several nodes
Hi, You would need the joint probability distribution of the nodes you are interested in. Unfortunately, it is not possible to acquire such a distribution in GeNIe directly, but it is possible to manually try and acquire what you need. Don't know how feasible it will be to do it by hand though. We'v...
- Sun Aug 12, 2012 12:21 am
- Forum: GeNIe
- Topic: where can I find 'tutorial17.xdsl'?
- Replies: 1
- Views: 2635
Re: where can I find 'tutorial17.xdsl'?
Hi,
It's not part of the GeNIe installation, it actually didn't exist yet
The wiki page was never finished.
I have created it and you can find a link to tutorial17.xdsl on the page.
https://genie.sis.pitt.edu/wiki/GeNIe_T ... n_Networks
Best,
Martijn
It's not part of the GeNIe installation, it actually didn't exist yet
The wiki page was never finished.
I have created it and you can find a link to tutorial17.xdsl on the page.
https://genie.sis.pitt.edu/wiki/GeNIe_T ... n_Networks
Best,
Martijn
- Sun Jun 03, 2012 4:44 am
- Forum: SMILE
- Topic: Issue with function "learn" SMILE error -1
- Replies: 2
- Views: 3691
Re: Issue with function "learn" SMILE error -1
Hi Sumin,
Most likely you'll need to correct:
naive.setClassVariableId("type");
Check if the column name is exactly "type"
To be safe you could check if the input file works properly in GeNIe.
Best,
Martijn
Most likely you'll need to correct:
naive.setClassVariableId("type");
Check if the column name is exactly "type"
To be safe you could check if the input file works properly in GeNIe.
Best,
Martijn
- Thu May 10, 2012 12:00 am
- Forum: GeNIe
- Topic: Bayesian search learning algorithm
- Replies: 1
- Views: 4434
Re: Bayesian search learning algorithm
Hi, There's useful information in the SMILE documentation, http://genie.sis.pitt.edu/wiki/Reference_Manual:_DSL_bs You'll find explanation of the parameters that can be set there. Basically the algorithm does a hill climbing search with random restarts. The BDeu metric is used for the scoring of the...