io.improbable.keanu.algorithms.variational.optimizer.gradient

Class ProbabilityFitnessFunctionGradient

java.lang.Object

io.improbable.keanu.algorithms.variational.optimizer.gradient.ProbabilityFitnessFunctionGradient

All Implemented Interfaces:

FitnessFunctionGradient

Direct Known Subclasses:

LogLikelihoodFitnessFunctionGradient, LogProbFitnessFunctionGradient

public abstract class ProbabilityFitnessFunctionGradient
extends java.lang.Object
implements FitnessFunctionGradient

Constructor Summary

Constructors

Constructor and Description
ProbabilityFitnessFunctionGradient(ProbabilisticModelWithGradient probabilisticModelWithGradient)

Method Summary

Modifier and Type	Method and Description
java.util.Map<? extends VariableReference,DoubleTensor>	getGradientsAt(java.util.Map<VariableReference,DoubleTensor> values)

Methods inherited from class java.lang.Object

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

Constructor Detail

ProbabilityFitnessFunctionGradient

public ProbabilityFitnessFunctionGradient(ProbabilisticModelWithGradient probabilisticModelWithGradient)

Method Detail

getGradientsAt

public java.util.Map<? extends VariableReference,DoubleTensor> getGradientsAt(java.util.Map<VariableReference,DoubleTensor> values)

Specified by:

getGradientsAt in interface FitnessFunctionGradient

Parameters:

values - the values of the variables in the fitness function.

Returns:

The gradient of the fitness function with respect to each of the variables specified in values at the values specified.