Thanks, so for the discrete EM we are actually filling in the missing data with expected values and then use the complete data to learn parameters.

Peng

## Search found 15 matches

- Mon Sep 03, 2018 12:31 pm
- Forum: SMILE
- Topic: EM algorithm for discrete model in GeNIe
- Replies:
**2** - Views:
**2291**

- Sat Sep 01, 2018 9:14 am
- Forum: SMILE
- Topic: EM algorithm for discrete model in GeNIe
- Replies:
**2** - Views:
**2291**

### EM algorithm for discrete model in GeNIe

Hi, it seems most materials available online are explaining the EM for GMM models, i.e. generate expected sufficient statistics for Gaussians.

But how EM works on discrete models? Especially the algorithm used in GeNIe? Can I ask for a reference or simple explanations? Thanks a lot.

Peng

But how EM works on discrete models? Especially the algorithm used in GeNIe? Can I ask for a reference or simple explanations? Thanks a lot.

Peng

- Thu Mar 16, 2017 9:33 am
- Forum: SMILE
- Topic: SMILE and GENIE structure learning
- Replies:
**3** - Views:
**2075**

### Re: SMILE and GENIE structure learning

It just runs for a long time. Thanks. I changed from debug mode to release mode.

- Thu Mar 16, 2017 4:13 am
- Forum: SMILE
- Topic: Error message when update net beliefs
- Replies:
**2** - Views:
**1794**

### Re: Error message when update net beliefs

many thanks it works.

- Thu Mar 16, 2017 2:33 am
- Forum: SMILE
- Topic: SMILE and GENIE structure learning
- Replies:
**3** - Views:
**2075**

### Re: SMILE and GENIE structure learning

I'm using VS2015

- Wed Mar 15, 2017 8:26 am
- Forum: SMILE
- Topic: Error message when update net beliefs
- Replies:
**2** - Views:
**1794**

### Error message when update net beliefs

I've leaned network structure with 2100 variables using gtt. When I update the network there is some errors:

Error (-42): UpdateBeliefs failed - network structure is too complex.

Could you please help sovle this?

many thanks

snowave

Error (-42): UpdateBeliefs failed - network structure is too complex.

Could you please help sovle this?

many thanks

snowave

- Wed Mar 15, 2017 4:34 am
- Forum: SMILE
- Topic: SMILE and GENIE structure learning
- Replies:
**3** - Views:
**2075**

### SMILE and GENIE structure learning

Hi, I have a relatively large dataset with 2500 features. I use SMILE and GENIE to perform greedy thick thinning structure learning. SMILE (in C++) seems going to run infinitely long without a response. GENIE, when using max num of parents=3, runs for 7 minutes and pop an error. If instead, of using...

### jsmile EM

Hi, I'm trying to use jsmile EM functionality. Is there an example/ tutorial for that?

I have problems to use the function learn(), which has a parameter DataMatch[] matching to pass in. How to set DataMatch [] matching?

Thanks

snowave

I have problems to use the function learn(), which has a parameter DataMatch[] matching to pass in. How to set DataMatch [] matching?

Thanks

snowave

- Thu Jan 12, 2017 6:58 am
- Forum: SMILE
- Topic: syscoordinate allocation
- Replies:
**1** - Views:
**1473**

### syscoordinate allocation

Hi , I'm trying to enter data as evidence to a v-structure A->C<-B and allocate the corresponding probability value in node C's CPT. For example, if all my nodes are binary nodes, with two states T and F, with observation {T,F,T} for A, B and C. How can I allocate the specific probability value in C...

- Thu Jan 12, 2017 2:50 am
- Forum: SMILE
- Topic: how probability of evidence is calculated
- Replies:
**5** - Views:
**2771**

### Re: how probability of evidence is calculated

yes, I mean the node definition, conditional probability. I think this can be used to calculate the probability of evidence by chain rule.

- Wed Jan 11, 2017 8:45 am
- Forum: SMILE
- Topic: structure learning problem
- Replies:
**1** - Views:
**1532**

### structure learning problem

hi, I have read my dataset into the ds object, i'm running structure learning below: cout << "\nstructure learning1..." << endl; DSL_greedyThickThinning gtt; DSL_network net2; if (gtt.Learn(ds, net2) != DSL_OKAY) { cout << "Cannot learn structure... exiting." << endl; exit(7); } net2.WriteFile("stor...

- Wed Jan 11, 2017 7:31 am
- Forum: SMILE
- Topic: how probability of evidence is calculated
- Replies:
**5** - Views:
**2771**

### Re: how probability of evidence is calculated

thanks for the answers.

Can I ask one more question? How to access each probability table associated with each node in the Network? I want to try to calculate the probability of evidence by chain rule but using a subset of all the probability tables.

many thanks

snowave

Can I ask one more question? How to access each probability table associated with each node in the Network? I want to try to calculate the probability of evidence by chain rule but using a subset of all the probability tables.

many thanks

snowave

- Fri Jan 06, 2017 2:56 am
- Forum: SMILE
- Topic: how probability of evidence is calculated
- Replies:
**5** - Views:
**2771**

### how probability of evidence is calculated

Hi, Can I ask how the probability of evidence is calculated in SMILE?

As far as I know, the pe is queried by summing over all possible states which mean the space is exponential. So How Smile does that?

thanks

Peng

As far as I know, the pe is queried by summing over all possible states which mean the space is exponential. So How Smile does that?

thanks

Peng

- Thu Jan 05, 2017 7:09 am
- Forum: SMILE
- Topic: How to calculate the joint distribution
- Replies:
**3** - Views:
**3259**

### How to calculate the joint distribution

Hi, I'm trying to calculate the joint distribution over a subset of the full joint distribution defined by the Bayesian net.

Is there an algorithm/method could do that using SMILE? thanks

Peng

Is there an algorithm/method could do that using SMILE? thanks

Peng

- Wed Jan 04, 2017 10:15 am
- Forum: SMILE
- Topic: set evidence to model using data
- Replies:
**1** - Views:
**1551**

### set evidence to model using data

Hi, I have been trying to set evidence to my model using my own data. I read all tutorials but I found no exact information on how to set evidence to each node in the model using data file. Can anyone help? Thanks What I need is the probability of evidence of each data record in my model. My code (i...