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

R

range(double, double) - Method in class mklab.JGNN.core.Slice

Performs the Slice.range(int, int) operation while replacing values of from and end with (int)(from*size()) and (int)(end*size()) so that fractional ranges can be obtained.

range(int, int) - Method in class mklab.JGNN.core.Slice

Obtains the identifiers in a given range of the (shuffled) slice.

Range - Class in mklab.JGNN.core.util

Implements an iterator that traverses a range [min, max) where the right side is non-inclusive.

Range(long, long) - Constructor for class mklab.JGNN.core.util.Range

Initializes a range [min, max) of subsequent integers where the right side is non-inclusive.

Range2D - Class in mklab.JGNN.core.util

Implements an iterator that traverses a two-dimensional range (min, max) x (min2, max2).

Range2D(long, long, long, long) - Constructor for class mklab.JGNN.core.util.Range2D

Reduce - Class in mklab.JGNN.nn.operations

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

register(double[]) - Method in class mklab.JGNN.core.Memory.Scope

regularization - Variable in class mklab.JGNN.nn.inputs.Parameter

regularization - Variable in class mklab.JGNN.nn.optimizers.Regularization

Regularization - Class in mklab.JGNN.nn.optimizers

Wraps an Optimizer by applying the derivative of L2 loss on every tensor during Optimizer.update(Tensor, Tensor).

Regularization() - Constructor for class mklab.JGNN.nn.optimizers.Regularization

Regularization(Optimizer, double) - Constructor for class mklab.JGNN.nn.optimizers.Regularization

Initializes a Regularization.

release() - Method in class mklab.JGNN.core.empty.EmptyMatrix

release() - Method in class mklab.JGNN.core.empty.EmptyTensor

release() - Method in class mklab.JGNN.core.matrix.AccessCol

release() - Method in class mklab.JGNN.core.matrix.AccessRow

release() - Method in class mklab.JGNN.core.matrix.ColumnRepetition

release() - Method in class mklab.JGNN.core.matrix.DenseMatrix

release() - Method in class mklab.JGNN.core.matrix.Diagonal

release() - Method in class mklab.JGNN.core.matrix.RepeatMatrix

release() - Method in class mklab.JGNN.core.matrix.RowRepetition

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

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

Deprecated.

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

release() - Method in class mklab.JGNN.core.matrix.VectorizedMatrix

release() - Method in class mklab.JGNN.core.matrix.WrapCols

release() - Method in class mklab.JGNN.core.matrix.WrapRows

release() - Method in class mklab.JGNN.core.tensor.AccessSubtensor

release() - Method in class mklab.JGNN.core.tensor.DenseTensor

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

Deprecated.

This method may not be present in future versions of the library, depending on whether memory reuse proves useful or nor.

release() - Method in class mklab.JGNN.core.tensor.RepeatTensor

release() - Method in class mklab.JGNN.core.tensor.SparseTensor

release() - Method in class mklab.JGNN.core.tensor.VectorizedTensor

release(double[]) - Static method in class mklab.JGNN.core.Memory

relu(double) - Static method in interface mklab.JGNN.core.util.Loss

The relu activation x if x > 0, 0 otherwise

relu(Tensor) - Static method in interface mklab.JGNN.core.util.Loss

Applies Loss.relu(double) element-by-element.

Relu - Class in mklab.JGNN.nn.activations

Implements a NNOperation that performs a relu transformation of its one input tensor.

Relu() - Constructor for class mklab.JGNN.nn.activations.Relu

reluDerivative(double) - Static method in interface mklab.JGNN.core.util.Loss

The derivative of the Loss.relu(double) function.

reluDerivative(Tensor) - Static method in interface mklab.JGNN.core.util.Loss

Applies Loss.reluDerivative(double) function.

rememberAs(String) - Method in class mklab.JGNN.adhoc.parsers.FastBuilder

Remembers the last layer's output per a given identifier so that {layerId} within future FastBuilder.layer(String) definitions is made to refer to the current layer.

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

Sets the current layer identifier to a specific symbol layerId so that future usage of {layerId} is automatically replaced with the identifier.

Repeat - 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.

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

Repeat1DIterator() - Constructor for class mklab.JGNN.core.matrix.ColumnRepetition.Repeat1DIterator

Repeat1DIterator() - Constructor for class mklab.JGNN.core.matrix.RowRepetition.Repeat1DIterator

Repeat2DIterator() - Constructor for class mklab.JGNN.core.matrix.ColumnRepetition.Repeat2DIterator

Repeat2DIterator() - Constructor for class mklab.JGNN.core.matrix.RowRepetition.Repeat2DIterator

RepeatMatrix - Class in mklab.JGNN.core.matrix

Implements a Matrix whose elements are all equals.

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

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

RepeatTensor - Class in mklab.JGNN.core.tensor

This class provides Tensor whose elements are all equal.

RepeatTensor(double, long) - Constructor for class mklab.JGNN.core.tensor.RepeatTensor

reset() - Method in interface mklab.JGNN.nn.Optimizer

Resets (and lets the garbage collector free) optimizer memory.

reset() - Method in class mklab.JGNN.nn.optimizers.Adam

reset() - Method in class mklab.JGNN.nn.optimizers.BatchOptimizer

reset() - Method in class mklab.JGNN.nn.optimizers.GradientDescent

reset() - Method in class mklab.JGNN.nn.optimizers.Regularization

Reshape - Class in mklab.JGNN.nn.operations

Implements a NNOperation that reshapes a matrix.

Reshape(long, long) - Constructor for class mklab.JGNN.nn.operations.Reshape

row - Variable in class mklab.JGNN.core.matrix.RowRepetition

RowRepetition - Class in mklab.JGNN.core.matrix

Defines a matrix whose rows are all a copy of a Tensor.

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

Instantiates a matrix repeating a tensor to be treated as a row.

RowRepetition.Repeat1DIterator - Class in mklab.JGNN.core.matrix

RowRepetition.Repeat2DIterator - Class in mklab.JGNN.core.matrix

run(List<Tensor>) - Method in class mklab.JGNN.nn.NNOperation

Performs a forward pass in the operation without inducing any kind of learning or storing the outcome.

run(Tensor...) - Method in class mklab.JGNN.nn.NNOperation

Performs a forward pass in the operation without inducing any kind of learning or storing the outcome.

runModel(ArrayList<Tensor>) - Method in class mklab.JGNN.adhoc.ModelBuilder

This is a wrapper for getModel().predict(inputs) without returning output values (use ModelBuilder.get(String) afterwards to view outputs.

runModel(Tensor...) - Method in class mklab.JGNN.adhoc.ModelBuilder

This is a wrapper for getModel().predict(inputs) without returning output values (use ModelBuilder.get(String) afterwards to view outputs.

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

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

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