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

Provides gradient based learning algorithms.

See: Description

Interface Summary

Interface	Description
GradientDescendable	Defines the functionality of an object that is required in order to apply the gradient descent algorithm to it.
ParameterGradientEvaluator<InputType,OutputType,GradientType>	Interface for computing the derivative of the output with respect to the parameters for a given input.

Class Summary

Class	Description
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