Package gov.sandia.cognition.learning.function.vector

Provides functions that output vectors.

See:
          Description

Class Summary
DifferentiableFeedforwardNeuralNetwork A feedforward neural network that can have an arbitrary number of layers, and an arbitrary differentiable squashing (activation) function assigned to each layer.
DifferentiableGeneralizedLinearModel A GradientDescenable version of a GeneralizedLinearModel, in other words, a GeneralizedLinearModel where the squashing function is differentiable
ElementWiseDifferentiableVectorFunction An ElementWiseVectorFunction that is also a DifferentiableVectorFunction
ElementWiseVectorFunction A VectorFunction that operates on each element of the Vector indepenently of all others.
EntropyEvaluator Takes a vector of inputs and computes the log base 2 entropy of the input.
FeedforwardNeuralNetwork A feedforward neural network that can have an arbitrary number of layers, and an arbitrary squashing (activation) function assigned to each layer.
GaussianContextRecognizer Uses a MixtureOfGaussians to compute the probability of the different constituent MultivariateGaussians (that is, the contexts)
GaussianContextRecognizer.Learner Creates a GaussianContextRecognizer from a Dataset using a BatchClusterer
GeneralizedLinearModel A VectorizableVectorFunction that is a matrix multiply followed by a VectorFunction...
LinearCombinationVectorFunction A weighted linear combination of scalar functions.
LinearVectorFunction The LinearFunction class is a simple VectorFunction that just scales the given input vector by a scalar value.
MultivariateDiscriminant Allows learning algorithms (vectorizing, differentiating) on a matrix*vector multiply.
MultivariateDiscriminantWithBias A multivariate discriminant (matrix multiply) plus a constant vector that gets added to the output of the discriminant.
ScalarBasisSet<InputType> Collection of scalar basis functions, where the ith function operates on the ith element of the output Vector
SubVectorEvaluator Extracts the given set of indices from an input vector to create a new vector containing the input vector's elements at those indices.
ThreeLayerFeedforwardNeuralNetwork This is a "standard" feedforward neural network with a single hidden layer.
VectorizableVectorConverter The VectorizableVectorConverter class implements a conversion between a Vectorizable and an Vector by calling the proper conversion method on the Vectorizable.
VectorizableVectorConverterWithBias The VectorizableVectorConverterWithBias class extends the VectorizableVectorConverter class to append a constant bias value of 1.0 to the vector returned by the converter.
 

Package gov.sandia.cognition.learning.function.vector Description

Provides functions that output vectors.

Since:
2.0
Author:
Justin Basilico