DSL_ALG_BN_LAURITZEN and DSL_ALG_BN_LSAMPLING

The engine.
Post Reply
Christian
Posts: 44
Joined: Wed Nov 28, 2007 12:32 pm

DSL_ALG_BN_LAURITZEN and DSL_ALG_BN_LSAMPLING

Post by Christian » Thu Dec 06, 2007 2:50 pm

Hello, I am just trying the API, but have problems to figure out the exact name of the algorithm in relation to the used constants.
I looked in the C# and C++ help


I think I figured out that DSL_ALG_BN_LAURITZEN is the clustering algorithm.

Is DSL_ALG_BN_LSAMPLING the logic sampling or the likelihood sampling algorithm?

As the likelihood algorithm seems to be very fast (3.2ms for a 20 million cpt network), but the results are not that good, can I just call updateBeliefs about 20 times and use the averages? Or is that something that will not help that much?

Which algorithm are you using normally for such big networks if you want the best relation between speed and accuracy?

Thank you very much,

Christian

shooltz[BayesFusion]
Site Admin
Posts: 1247
Joined: Mon Nov 26, 2007 5:51 pm

Re: DSL_ALG_BN_LAURITZEN and DSL_ALG_BN_LSAMPLING

Post by shooltz[BayesFusion] » Thu Dec 06, 2007 3:00 pm

Increase the number of samples with DSL_network::SetNumberOfSamples. The default is 1000, which is certainly too low for huge CPT you have.

You may also try DSL_ALG_BN_EPISSAMPLING.

Post Reply