Search found 76 matches
- Tue Apr 17, 2012 8:16 am
- Forum: GeNIe
- Topic: Test designed network
- Replies: 7
- Views: 6430
Re: Test designed network
Did you perhaps get any error messages? When validating, a dataset file needs to be open and a (learned) network. Next steps is matching the nodes in the network and the columns in the data file, this usually happens automatically (the finished result is in the center column, unmatched nodes and col...
- Mon Apr 16, 2012 12:52 pm
- Forum: GeNIe
- Topic: Test designed network
- Replies: 7
- Views: 6430
Re: Test designed network
Hi Pratibha,
What seems to be the problem?
What seems to be the problem?
- Fri Apr 13, 2012 2:16 am
- Forum: GeNIe
- Topic: GeNIe Feature Suggestion: At-a-glance probability visual...
- Replies: 3
- Views: 4024
Re: GeNIe Feature Suggestion: At-a-glance probability visual
Hi, GeNIe can actually do this as well. Try the following: 1. Select all the nodes 2. right click on a node 3. from the context menu select view as -> bar chart 4. From the Network menu select Update immediatly Now you'll see the distribution of all the nodes. If you double click on one of the state...
- Thu Mar 08, 2012 4:53 pm
- Forum: SMILE
- Topic: Inference algorithms in SMILE
- Replies: 2
- Views: 5470
Re: Inference algorithms in SMILE
Hi Jonnie, Sorry for the long wait on this one. Tying up loose ends as much as possible. Answering in the same order as asked The issues: - I've added references in the documentation for the papers in the two wiki pages you have mentioned now have links to the papers - Good point, the name differenc...
Re: DBNs
Hi Mouhamad,
Could you give some more details on your network, i.e. number of (temporal) arcs.
Or perhaps PM or email me (genie@sis.pitt.edu) your network so I can have a look if I see similar results?
Best,
Martijn
Could you give some more details on your network, i.e. number of (temporal) arcs.
Or perhaps PM or email me (genie@sis.pitt.edu) your network so I can have a look if I see similar results?
Best,
Martijn
- Thu Mar 08, 2012 3:40 pm
- Forum: SMILE
- Topic: node->Info().Screen().color returns wrong RGB String
- Replies: 7
- Views: 7537
Re: node->Info().Screen().color returns wrong RGB String
Thales, I have tried it myself and have seen the same result. I can't say yet if this is by design or a bug, the person that is most familiar with this code is still on holiday. I have added a ticket to our internal bug tracking system and once I know more I'll report back here in this thread. Best,...
- Wed Mar 07, 2012 3:37 am
- Forum: SMILE
- Topic: SMILE source code
- Replies: 8
- Views: 9844
Re: SMILE source code
Hi Sutambe,
SMILE is not open source software.
I'll contact you over email to see if we can work out a way to compile it for your platform.
Best,
Martijn
(PhD Student, Decision Systems Lab)
SMILE is not open source software.
I'll contact you over email to see if we can work out a way to compile it for your platform.
Best,
Martijn
(PhD Student, Decision Systems Lab)
- Tue Mar 06, 2012 7:43 pm
- Forum: SMILE
- Topic: node->Info().Screen().color returns wrong RGB String
- Replies: 7
- Views: 7537
Re: node->Info().Screen().color returns wrong RGB String
Hi Thales,
I'm looking into the problem.
Just to double check, if you load the network in GeNIe, are the colors then as you expect?
Best,
Martijn
I'm looking into the problem.
Just to double check, if you load the network in GeNIe, are the colors then as you expect?
Best,
Martijn
- Sun Feb 26, 2012 11:39 pm
- Forum: SMILE
- Topic: Finding the Algorithm Papers
- Replies: 1
- Views: 3159
Re: Finding the Algorithm Papers
Hi Jonnie, I have updated the wiki so that the papers now have links. For the UAI related papers I have tried to use uai.sis.pitt.edu links as much as possible. Where possible I have added Workshop paper links for some of the missing UAI papers that were in the UAI books, which are not allowed to be...
- Sun Feb 19, 2012 8:17 pm
- Forum: GeNIe
- Topic: Genie Sampling and fixed nodes
- Replies: 19
- Views: 14615
Re: Genie Sampling and fixed nodes
Yes, that means that as long as I'm not sure about my evidence, the sampling helps me to verify. I don't quite understand what you mean by this. Why and how would sampling help you verify the evidence? Maybe you somehow relate the sampling to the evidence you provide, I don't think that's right. Ma...
- Sun Feb 19, 2012 8:11 pm
- Forum: SMILE
- Topic: different results for Genie and Smile
- Replies: 23
- Views: 19731
Re: different results for Genie and Smile
Why are all the states of the nodes uniformly distributed? That surprises me a bit. You mention setting priors later for some node, why not just set these prior distributions in the nodes the network itself (as in setting the values in genie and saving the network)? So, you have 21 class nodes, whic...
- Sun Feb 19, 2012 7:42 pm
- Forum: GeNIe
- Topic: Genie Sampling and fixed nodes
- Replies: 19
- Views: 14615
Re: Genie Sampling and fixed nodes
Well, hard evidence means basically your are absolute sure. Let's say in a weather model you observe it's raining. There's no discusion and setting this evidence 'raining' in the node translates into giving it a probability distribution of 1.0 for 'raining' and 0 for any other option here In Genie y...
- Sun Feb 19, 2012 7:37 pm
- Forum: SMILE
- Topic: different results for Genie and Smile
- Replies: 23
- Views: 19731
Re: different results for Genie and Smile
Ok. Can you summarize the whole procedure for both your code and Genie? Is it basically: 1. Set evidence for a number of nodes (for how many nodes, do you set soft evidence?, how many nodes do not receive any evidence?) 2. Run inference 3. Check probabilities (how do you check them in the code? how ...
- Sun Feb 19, 2012 7:26 pm
- Forum: GeNIe
- Topic: Genie Sampling and fixed nodes
- Replies: 19
- Views: 14615
Re: Genie Sampling and fixed nodes
The basic idea of sampling algorithms for BN inference is that you generate samples from the network, i.e. for every node you randomly pick a value depending on it's (conditional) probability distribution and any evidence set (hard or soft). So you do for a while and generate like 10000 samples. Fro...
- Sun Feb 19, 2012 7:16 pm
- Forum: SMILE
- Topic: different results for Genie and Smile
- Replies: 23
- Views: 19731
Re: different results for Genie and Smile
Ok, I see.
So, just to make sure everything is completely clear, could you post the code segment as it is exactly?
So, just to make sure everything is completely clear, could you post the code segment as it is exactly?