tmpLearn
Class NaiveDNLearner
java.lang.Object
infer.Infer
tmpLearn.Learner
tmpLearn.NaiveDNLearner
public class NaiveDNLearner
- extends Learner
Learner instance using diagonal Newton.
Note, this is a very simple diagonal Newton
learner. When use it for real circumstance,
please check it carefully...
Field Summary |
double |
alpha
|
double |
lambda
|
int |
nCall
|
java.util.HashMap<java.lang.String,java.lang.Double> |
oldD
|
double |
oldDG
|
double |
oldDHD
|
java.util.HashMap<java.lang.String,java.lang.Double> |
oldDW
|
java.util.HashMap<java.lang.String,java.lang.Double> |
oldG
|
Fields inherited from class tmpLearn.Learner |
backtrackCount_, backtracked, currentD, currentWeight, finalWeight, isFirstTime, isHardMappings, odds, oldWeight, trainingSatisification, trainingViolation |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
alpha
public double alpha
lambda
public double lambda
nCall
public int nCall
oldD
public java.util.HashMap<java.lang.String,java.lang.Double> oldD
oldDG
public double oldDG
oldDHD
public double oldDHD
oldDW
public java.util.HashMap<java.lang.String,java.lang.Double> oldDW
oldG
public java.util.HashMap<java.lang.String,java.lang.Double> oldG
NaiveDNLearner
public NaiveDNLearner()
loadingTrainingData
public void loadingTrainingData(MCSAT _mcsat)
- Loading training data's truth value into MRF.
- Specified by:
loadingTrainingData
in class Learner
- Parameters:
_mcsat
- The MCSAT object to be filled in.
updateWeight
public boolean updateWeight(MCSAT mcsat)
- Updating
Learner.currentWeight
using Diagonal
Newton method.
- Specified by:
updateWeight
in class Learner
- Parameters:
mcsat
- MCSAT instance after this iteration.
- Returns:
- Whether terminate.