Package gov.sandia.cognition.learning.algorithm.gradient

Provides gradient based learning algorithms.

See:
          Description

Interface Summary
GradientDescendable The GradientDescendable interface defines the functionality of an object that is required in order to apply the gradient descent algorithm to it.
ParameterGradientEvaluator<InputOutputType,GradientType> Interface for computing the derivative of the output with respect to the parameters for a given input.
 

Class Summary
GradientDescendableApproximator Creates a radientDescendable from a VectorizableVectorFunction by estimating the parameter gradient using a forward-difference approximation of the parameter Jacobian.
 

Package gov.sandia.cognition.learning.algorithm.gradient Description

Provides gradient based learning algorithms. This includes Gradient Descent and the Levenberg-Marquart algorithm.

Since:
2.0
Author:
Justin Basilico