gov.sandia.cognition.learning.algorithm.gradient
Interface ParameterGradientEvaluator<InputOutputType,GradientType>

Type Parameters:
InputOutputType - Input and Output classes of the Evaluator, such as Vector, for example
GradientType - Class type of the gradient, such as Matrix, for example
All Superinterfaces:
Cloneable, CloneableSerializable, Evaluator<InputOutputType,InputOutputType>, Serializable, Vectorizable
All Known Subinterfaces:
GradientDescendable
All Known Implementing Classes:
DifferentiableFeedforwardNeuralNetwork, DifferentiableGeneralizedLinearModel, GradientDescendableApproximator, MultivariateDiscriminant, MultivariateDiscriminantWithBias, PolynomialFunction, ThreeLayerFeedforwardNeuralNetwork

@CodeReview(reviewer="Kevin R. Dixon",
            date="2008-07-23",
            changesNeeded=false,
            comments={"Minor change to javadoc.","Looks fine."})
public interface ParameterGradientEvaluator<InputOutputType,GradientType>
extends Evaluator<InputOutputType,InputOutputType>, Vectorizable

Interface for computing the derivative of the output with respect to the parameters for a given input.

Since:
2.0
Author:
Kevin R. Dixon

Method Summary
 GradientType computeParameterGradient(InputOutputType input)
          Computes the derivative of the output with respect to the parameters for a particular input.
 
Methods inherited from interface gov.sandia.cognition.evaluator.Evaluator
evaluate
 
Methods inherited from interface gov.sandia.cognition.math.matrix.Vectorizable
clone, convertFromVector, convertToVector
 

Method Detail

computeParameterGradient

GradientType computeParameterGradient(InputOutputType input)
Computes the derivative of the output with respect to the parameters for a particular input.

Parameters:
input - Input about which to compute the parameter gradient
Returns:
Change of the parameters with respect to the output