I know the log likelihood is calculated with in the EM and other learning algorithms, but does there exist a function that takes an existing network and a dataset, then calculates the log likelihood sore, without necessarily learning parameters?
If not can you tell me how the log likelihood is calculated within the EM algorithm.
Thank you
is there a function for calculating the log likelihood?
-
- Posts: 11
- Joined: Mon Dec 11, 2023 8:20 pm
-
- Site Admin
- Posts: 1422
- Joined: Mon Nov 26, 2007 5:51 pm
Re: is there a function for calculating the log likelihood?
Sorry for the late reply.
The most recent GeNIe build, version 4.1.3724, has a command which calculates the log likelihood for the network/dataset combination. This is implemented by calculating the sum of log(P(E)) values for each record in the dataset.
SMILE will support this functionality in its next release.
The most recent GeNIe build, version 4.1.3724, has a command which calculates the log likelihood for the network/dataset combination. This is implemented by calculating the sum of log(P(E)) values for each record in the dataset.
SMILE will support this functionality in its next release.