gov.sandia.cognition.learning.function.cost

Interface DifferentiableCostFunction

All Superinterfaces:

java.lang.Cloneable, CloneableSerializable, CostFunction<Evaluator<? super Vector,? extends Vector>,java.util.Collection<? extends InputOutputPair<? extends Vector,Vector>>>, Evaluator<Evaluator<? super Vector,? extends Vector>,java.lang.Double>, PerformanceEvaluator<Evaluator<? super Vector,? extends Vector>,java.util.Collection<? extends InputOutputPair<? extends Vector,Vector>>,java.lang.Double>, java.io.Serializable, Summarizer<TargetEstimatePair<? extends Vector,? extends Vector>,java.lang.Double>, SupervisedCostFunction<Vector,Vector>, SupervisedPerformanceEvaluator<Vector,Vector,Vector,java.lang.Double>

All Known Subinterfaces:

ParallelizableCostFunction

All Known Implementing Classes:

AbstractParallelizableCostFunction, MeanSquaredErrorCostFunction, ParallelizedCostFunctionContainer, SumSquaredErrorCostFunction

public interface DifferentiableCostFunction
extends SupervisedCostFunction<Vector,Vector>

The DifferentiableCostFunction is a cost function that can be differentiated. This requires that it operate as a cost function for VectorFunction objects and it has a separate method for doing the differentiation of a given DifferentiableVectorFunction with respect to the cost function.

Since:

1.0

Author:

Kevin R. Dixon

Method Summary

Modifier and Type	Method and Description
Vector	computeParameterGradient(GradientDescendable function) Differentiates function with respect to its parameters.

Methods inherited from interface gov.sandia.cognition.learning.function.cost.CostFunction

clone, evaluate, getCostParameters, setCostParameters

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

summarize

Methods inherited from interface gov.sandia.cognition.learning.performance.SupervisedPerformanceEvaluator

evaluatePerformance

Methods inherited from interface gov.sandia.cognition.learning.performance.PerformanceEvaluator

evaluatePerformance

Method Detail

computeParameterGradient

Vector computeParameterGradient(GradientDescendable function)

Differentiates function with respect to its parameters.

Parameters:

function - The object to differentiate.

Returns:

Derivatives of the object with respect to the cost function.