CRF (version 0.3-8)

train.mrf: Train MRF model

Description

Train the MRF model to estimate the parameters

Usage

train.mrf(crf, instances, nll = mrf.nll, trace = 0)

Arguments

crf

The CRF

instances

The training data matrix of CRF model

nll

The function to calculate negative log likelihood

trace

Non-negative integer to control the tracing informtion of the optimization process

Value

• This function will directly modify the CRF and return the same CRF.

Details

This function trains the Markov Random Fields (MRF) model, which is a simple variant of CRF model.

In the training data matrix instances, each row is an instance and each column corresponds a node in CRF.

See Also

mrf.update, mrf.stat, mrf.nll, make.crf