Index

A B C D E F G H I K L M N O P Q R S T U V W X Z
All Classes and Interfaces|All Packages

V

validationLoss - Variable in class mklab.JGNN.adhoc.ModelTraining

values - Variable in class mklab.JGNN.core.tensor.DenseTensor

values - Variable in class mklab.JGNN.core.tensor.VectorizedTensor

var(String) - Method in class mklab.JGNN.adhoc.ModelBuilder

Declares a component with the given name to be used as an input of the managed model.

var(String) - Method in class mklab.JGNN.adhoc.parsers.LayeredBuilder

var(String) - Method in class mklab.JGNN.adhoc.parsers.Neuralang

Variable - Class in mklab.JGNN.nn.inputs

Implements a NNOperation that represents Model inputs.

Variable() - Constructor for class mklab.JGNN.nn.inputs.Variable

VariancePreservingInitializer - Class in mklab.JGNN.nn.initializers

This class describes a broad class of Initializer strategies, in which dense neural layer initialization is controlled so that variance is mostly preserved from inputs to outputs to avoid vanishing or exploding gradients in the first training runs.

VariancePreservingInitializer() - Constructor for class mklab.JGNN.nn.initializers.VariancePreservingInitializer

vectorization - Static variable in class mklab.JGNN.core.Tensor

VectorizedMatrix - Class in mklab.JGNN.core.matrix

Implements a dense Matrix where all elements are stored in memory.

VectorizedMatrix(long, long) - Constructor for class mklab.JGNN.core.matrix.VectorizedMatrix

Generates a dense matrix with the designated number of rows and columns.

VectorizedTensor - Class in mklab.JGNN.core.tensor

This class provides a dense Tensor that wraps an array of doubles.

VectorizedTensor() - Constructor for class mklab.JGNN.core.tensor.VectorizedTensor

VectorizedTensor(double...) - Constructor for class mklab.JGNN.core.tensor.VectorizedTensor

VectorizedTensor(long) - Constructor for class mklab.JGNN.core.tensor.VectorizedTensor

Constructs a dense tensor holding zero values.

VectorizedTensor(String) - Constructor for class mklab.JGNN.core.tensor.VectorizedTensor

Reconstructs a serialized Tensor (i.e.

VectorizedTensor(Iterator<? extends Number>) - Constructor for class mklab.JGNN.core.tensor.VectorizedTensor

Constructs a dense tensor from an iterator holding that outputs its values.

verbose - Variable in class mklab.JGNN.adhoc.ModelTraining

VerboseLoss - Class in mklab.JGNN.nn.loss.report

Implements a Loss that wraps other losses and outputs their value during training to an output stream (to System.out by default).

VerboseLoss(Loss...) - Constructor for class mklab.JGNN.nn.loss.report.VerboseLoss

Instantiates a VerboseLoss given one or more comma-separated base losses to be wrapped.

view() - Method in class mklab.JGNN.nn.NNOperation

Retrieves a string that views internal data being processed by the current thread, including gradients.

A B C D E F G H I K L M N O P Q R S T U V W X Z
All Classes and Interfaces|All Packages