gov.sandia.cognition.learning.function.cost
Interface DifferentiableCostFunction

All Superinterfaces:
Cloneable, CloneableSerializable, CostFunction<Evaluator<? super Vector,? extends Vector>,Collection<? extends InputOutputPair<? extends Vector,Vector>>>, Evaluator<Evaluator<? super Vector,? extends Vector>,Double>, PerformanceEvaluator<Evaluator<? super Vector,? extends Vector>,Collection<? extends InputOutputPair<Vector,Vector>>,Double>, Serializable, Summarizer<TargetEstimatePair<? extends Vector,? extends Vector>,Double>, SupervisedCostFunction<Vector,Vector>, SupervisedPerformanceEvaluator<Vector,Vector,Vector,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
 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.