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

D

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

Dataset - Class in mklab.JGNN.adhoc

This class provides the backbone with which to define datasets.

Dataset() - Constructor for class mklab.JGNN.adhoc.Dataset

debugging - Variable in class mklab.JGNN.nn.NNOperation

DenseMatrix - Class in mklab.JGNN.core.matrix

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

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

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

DenseTensor - Class in mklab.JGNN.core.tensor

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

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

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

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

Constructs a dense tensor holding zero values.

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

Reconstructs a serialized Tensor (i.e.

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

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

density() - Method in class mklab.JGNN.core.Tensor

Provides the memory allocation density of Tensor.getNonZeroElements() compare to the size of the tensor.

derivative(Tensor, Tensor) - Method in class mklab.JGNN.nn.loss.Accuracy

derivative(Tensor, Tensor) - Method in class mklab.JGNN.nn.loss.BinaryCrossEntropy

derivative(Tensor, Tensor) - Method in class mklab.JGNN.nn.loss.CategoricalCrossEntropy

derivative(Tensor, Tensor) - Method in class mklab.JGNN.nn.Loss

Provides the derivative of a loss function at its evaluation point.

derivative(Tensor, Tensor) - Method in class mklab.JGNN.nn.loss.report.VerboseLoss

describe() - Method in class mklab.JGNN.adhoc.ModelBuilder

Creates a description of the builded model's internal execution graph.

describe() - Method in class mklab.JGNN.core.Matrix

describe() - Method in class mklab.JGNN.core.matrix.SparseMatrix

describe() - Method in class mklab.JGNN.core.matrix.SparseSymmetric

Deprecated.

describe() - Method in class mklab.JGNN.core.matrix.TransposedMatrix

describe() - Method in class mklab.JGNN.core.Tensor

Describes the type, size and other characteristics of the tensor.

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

Retrieves a concise description of the operation that shows metadata and potential data descriptions processed by the current thread.

determineZeroCopy(Matrix, long, long, long) - Method in class mklab.JGNN.core.Matrix

determineZeroCopy(Tensor) - Method in class mklab.JGNN.core.Tensor

Automatically determines which between the tensor and a competitor is chosen create zero copies for two-argument operations.

Diagonal - Class in mklab.JGNN.core.matrix

Implements a square matrix whose diagonal elements are determined by the correspond values of an underlying tensor and off-diagonal elements are zero.

Diagonal(Tensor) - Constructor for class mklab.JGNN.core.matrix.Diagonal

Diagonal.Diagonal1DIterator - Class in mklab.JGNN.core.matrix

Diagonal.Diagonal2DIterator - Class in mklab.JGNN.core.matrix

Diagonal1DIterator(Iterator<Long>) - Constructor for class mklab.JGNN.core.matrix.Diagonal.Diagonal1DIterator

Diagonal2DIterator(Iterator<Long>) - Constructor for class mklab.JGNN.core.matrix.Diagonal.Diagonal2DIterator

Distribution - Interface in mklab.JGNN.core

This interface abstracts a probability distribution that can be passed to Tensor.setToRandom(Distribution) for random tensor initialization.

dot(Tensor) - Method in class mklab.JGNN.core.Tensor

Performs the dot product between this and another tensor.

dot(Tensor, Tensor) - Method in class mklab.JGNN.core.Tensor

Performs the triple dot product between this and two other tensors.

downloadIfNotExists(String, String) - Method in class mklab.JGNN.adhoc.Dataset

Dropout - Class in mklab.JGNN.nn.operations

Implements a NNOperation that converts its first argument to a ColumnRepetition matrix with a number of columns equal to the second argument.

Dropout() - Constructor for class mklab.JGNN.nn.operations.Dropout

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