Uses of Interface
gov.sandia.cognition.learning.algorithm.gradient.GradientDescendable

Packages that use GradientDescendable

Package	Description
gov.sandia.cognition.learning.algorithm.gradient	Provides gradient based learning algorithms.
gov.sandia.cognition.learning.algorithm.regression	Provides regression algorithms, such as Linear Regression.
gov.sandia.cognition.learning.function.cost	Provides cost functions.
gov.sandia.cognition.learning.function.vector	Provides functions that output vectors.

Uses of GradientDescendable in gov.sandia.cognition.learning.algorithm.gradient

Classes in gov.sandia.cognition.learning.algorithm.gradient that implement GradientDescendable

Modifier and Type	Class and Description
class	GradientDescendableApproximator Creates a radientDescendable from a VectorizableVectorFunction by estimating the parameter gradient using a forward-difference approximation of the parameter Jacobian.

Methods in gov.sandia.cognition.learning.algorithm.gradient that return GradientDescendable

Modifier and Type	Method and Description
GradientDescendable	GradientDescendable.clone() Creates a new clone (shallow copy) of this object.

Uses of GradientDescendable in gov.sandia.cognition.learning.algorithm.regression

Constructors in gov.sandia.cognition.learning.algorithm.regression with parameters of type GradientDescendable

Constructor and Description
ParameterCostEvaluatorDerivativeBased(GradientDescendable internalFunction, DifferentiableCostFunction costFunction) Creates a new instance of ParameterCostEvaluatorDerivativeBased

Uses of GradientDescendable in gov.sandia.cognition.learning.function.cost

Methods in gov.sandia.cognition.learning.function.cost with parameters of type GradientDescendable

Modifier and Type	Method and Description
static SumSquaredErrorCostFunction.Cache	SumSquaredErrorCostFunction.Cache.compute(GradientDescendable objectToOptimize, java.util.Collection<? extends InputOutputPair<? extends Vector,Vector>> data) Computes often-used parameters of a sum-squared error term
Vector	AbstractParallelizableCostFunction.computeParameterGradient(GradientDescendable function)
Vector	DifferentiableCostFunction.computeParameterGradient(GradientDescendable function) Differentiates function with respect to its parameters.
Vector	MeanSquaredErrorCostFunction.computeParameterGradient(GradientDescendable function)
Vector	ParallelizedCostFunctionContainer.computeParameterGradient(GradientDescendable function)
java.lang.Object	ParallelizableCostFunction.computeParameterGradientPartial(GradientDescendable function) Computes the partial (linear) component of the cost function gradient.
java.lang.Object	SumSquaredErrorCostFunction.computeParameterGradientPartial(GradientDescendable function)

Constructors in gov.sandia.cognition.learning.function.cost with parameters of type GradientDescendable

Constructor and Description
SubCostGradient(ParallelizableCostFunction costFunction, GradientDescendable evaluator) Creates a new instance of SubCostGradient

Uses of GradientDescendable in gov.sandia.cognition.learning.function.vector

Classes in gov.sandia.cognition.learning.function.vector that implement GradientDescendable

Modifier and Type	Class and Description
class	DifferentiableFeedforwardNeuralNetwork A feedforward neural network that can have an arbitrary number of layers, and an arbitrary differentiable squashing (activation) function assigned to each layer.
class	DifferentiableGeneralizedLinearModel A GradientDescenable version of a GeneralizedLinearModel, in other words, a GeneralizedLinearModel where the squashing function is differentiable
class	MultivariateDiscriminant Allows learning algorithms (vectorizing, differentiating) on a matrix*vector multiply.
class	MultivariateDiscriminantWithBias A multivariate discriminant (matrix multiply) plus a constant vector that gets added to the output of the discriminant.
class	ThreeLayerFeedforwardNeuralNetwork This is a "standard" feedforward neural network with a single hidden layer.