gov.sandia.cognition.statistics.distribution

Class MultivariateGaussian.MaximumLikelihoodEstimator

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.statistics.distribution.MultivariateGaussian.MaximumLikelihoodEstimator

All Implemented Interfaces:

BatchLearner<java.util.Collection<? extends Vector>,MultivariateGaussian.PDF>, DistributionEstimator<Vector,MultivariateGaussian.PDF>, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

Enclosing class:

MultivariateGaussian

public static class MultivariateGaussian.MaximumLikelihoodEstimator
extends AbstractCloneableSerializable
implements DistributionEstimator<Vector,MultivariateGaussian.PDF>

Computes the Maximum Likelihood Estimate of the MultivariateGaussian given a set of Vectors

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static double	DEFAULT_COVARIANCE Default covariance used in estimation, 1.0E-5.

Constructor Summary

Constructors

Constructor and Description
MaximumLikelihoodEstimator() Default constructor;
MaximumLikelihoodEstimator(double defaultCovariance) Creates a new instance of MaximumLikelihoodEstimator

Method Summary

Modifier and Type	Method and Description
MultivariateGaussian.PDF	learn(java.util.Collection<? extends Vector> data) Computes the Gaussian that estimates the maximum likelihood of generating the given set of samples.
static MultivariateGaussian.PDF	learn(java.util.Collection<? extends Vector> data, double defaultCovariance) Computes the Gaussian that estimates the maximum likelihood of generating the given set of samples.

Methods inherited from class gov.sandia.cognition.util.AbstractCloneableSerializable

clone

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable

clone

Field Detail

DEFAULT_COVARIANCE

public static final double DEFAULT_COVARIANCE

Default covariance used in estimation, 1.0E-5.

See Also:

Constant Field Values

Constructor Detail

MaximumLikelihoodEstimator

public MaximumLikelihoodEstimator()

Default constructor;

MaximumLikelihoodEstimator

public MaximumLikelihoodEstimator(double defaultCovariance)

Creates a new instance of MaximumLikelihoodEstimator

Parameters:

defaultCovariance - Amount to add to the diagonal of the covariance matrix

Method Detail

learn

public static MultivariateGaussian.PDF learn(java.util.Collection<? extends Vector> data,
                                             double defaultCovariance)

Computes the Gaussian that estimates the maximum likelihood of generating the given set of samples.

Parameters:

defaultCovariance - amount to add to the diagonals of the covariance matrix, typically on the order of 1e-4, can be 0.0.

data - The samples to calculate the Gaussian from throws IllegalArgumentException if samples has 1 or fewer samples.

Returns:

The Gaussian that estimates the maximum likelihood of generating the given data.

learn

public MultivariateGaussian.PDF learn(java.util.Collection<? extends Vector> data)

Computes the Gaussian that estimates the maximum likelihood of generating the given set of samples.

Specified by:

learn in interface BatchLearner<java.util.Collection<? extends Vector>,MultivariateGaussian.PDF>

Parameters:

data - The samples to calculate the Gaussian from throws IllegalArgumentException if samples has 1 or fewer samples.

Returns:

The Gaussian that estimates the maximum likelihood of generating the given data.