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

S

sample() - Method in class mklab.JGNN.core.distribution.Normal

sample() - Method in interface mklab.JGNN.core.Distribution

Retrieves a new sample from the distribution.

sample() - Method in class mklab.JGNN.core.distribution.Uniform

SampleClassification - Class in mklab.JGNN.adhoc.train

Extends the ModelTraining class to train Model instances from feature and label matrices.

SampleClassification() - Constructor for class mklab.JGNN.adhoc.train.SampleClassification

samples() - Method in class mklab.JGNN.adhoc.Dataset

Retrieves a converter that maps samples to long identifiers that match them to rows of Dataset.features(), Dataset.labels(), and Dataset.graph() matrices.

samplesAsFeatures() - Method in class mklab.JGNN.core.Slice

Constructs a column matrix holding identifiers in the range 0,1,..Slice.size()-1 so that the pattern slice.samplesAsFeatures().accessRows(slice.range(from, end)) retrieves one-element tensors holding slice[from], slice[from+1], ...

save(Path) - Method in class mklab.JGNN.adhoc.ModelBuilder

Serializes the model builder instance into a Path, such as Paths.get("example.jgnn").

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

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

scope() - Static method in class mklab.JGNN.core.Memory

Scripting - Class in nodeClassification

Demonstrates classification with an architecture defined through the scripting engine.

Scripting() - Constructor for class nodeClassification.Scripting

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

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

Performs in-memory set of each element to its absolute value.

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

selfAdd(double) - Method in class mklab.JGNN.core.Tensor

Performs in-memory addition to the Tensor, storing the result in itself.

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

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

Performs in-memory addition to the Tensor, storing the result in itself.

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

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

Performs in-memory weighted addition to the Tensor, storing the result in itself.

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

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

Sets the exponential minus 1 of tensor elements.

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

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

Performs in-memory the inverse of each non-zero element.

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

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

Performs in-memory set of each element to the logarithm of its absolute value.

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

selfMultiply(double) - Method in class mklab.JGNN.core.Tensor

Performs in-memory multiplication on the Tensor, storing the result to itself.

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

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

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

Performs in-memory multiplication on the Tensor, storing the result in itself .

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

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

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

Performs in-memory set of each element to the negative of itself.

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

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

Performs in-memory set of each element to the square root of its absolute value.

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

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

Performs in-memory subtraction from the Tensor, storing the result in itself.

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

set(Tensor) - Method in class mklab.JGNN.nn.inputs.Parameter

Forcefully sets the parameter's value tensor to the desired value.

setColName(String) - Method in class mklab.JGNN.core.Matrix

Sets a name for the matrix's column dimension.

setDescription(String) - Method in class mklab.JGNN.nn.NNOperation

setDeviation(double) - Method in class mklab.JGNN.core.distribution.Normal

setDeviation(double) - Method in interface mklab.JGNN.core.Distribution

Sets the standard deviation of the distribution.

setDeviation(double) - Method in class mklab.JGNN.core.distribution.Uniform

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

Sets the matrix's specified diagonal elements to a given value.

setDimensionName(String) - Method in class mklab.JGNN.core.Tensor

Sets a name for the tensor's one dimension.

setDimensionName(String) - Method in class mklab.JGNN.nn.pooling.Sort

setDimensionName(String, String) - Method in class mklab.JGNN.adhoc.IdConverter

Sets dimension names for one-hot encodings.

setDimensionName(String, String) - Method in class mklab.JGNN.core.Matrix

Sets a name for the matrix's row and column dimensions.

setDimensionName(String, String) - Method in class mklab.JGNN.nn.operations.Reshape

setDimensionName(Tensor) - Method in class mklab.JGNN.core.Matrix

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

Fills in dimension names per an example Tensor.isMatching(mklab.JGNN.core.Tensor) tensor.

setEnabled(boolean) - Method in class mklab.JGNN.nn.operations.Dropout

setEpochs(int) - Method in class mklab.JGNN.adhoc.ModelTraining

Sets the maximum number of epochs for which training runs.

setFeatures(Matrix) - Method in class mklab.JGNN.adhoc.train.SampleClassification

Sets the feature matrix of data samples, where each row corresponds to a different sample.

setGraphLabels(List<Tensor>) - Method in class mklab.JGNN.adhoc.train.AGFTraining

setGraphs(List<Matrix>) - Method in class mklab.JGNN.adhoc.train.AGFTraining

setInterval(int) - Method in class mklab.JGNN.nn.loss.report.VerboseLoss

Changes on which epochs the loss should be reported.

setKey(K) - Method in class mklab.JGNN.core.util.FastEntry

setLoss(Loss) - Method in class mklab.JGNN.adhoc.ModelTraining

Sets which Loss should be applied on training batches (the loss is averaged across batches, but is aggregated as a sum within each batch by BatchOptimizer).

setMainDiagonal(double) - Method in class mklab.JGNN.core.Matrix

Sets the matrix's specified main diagonal elements to a given value value.

setMean(double) - Method in class mklab.JGNN.core.distribution.Normal

setMean(double) - Method in interface mklab.JGNN.core.Distribution

Sets the mean of the distribution.

setMean(double) - Method in class mklab.JGNN.core.distribution.Uniform

setMeanReduction(boolean) - Method in class mklab.JGNN.nn.loss.CategoricalCrossEntropy

Sets the reduction mechanism of categorical cross entropy.

setNodeFeatures(List<Matrix>) - Method in class mklab.JGNN.adhoc.train.AGFTraining

setNumBatches(int) - Method in class mklab.JGNN.adhoc.ModelTraining

Sets the number of batches training data slices should be split into.

setOptimizer(Optimizer) - Method in class mklab.JGNN.adhoc.ModelTraining

Sets an Optimizer instance to controls parameter updates during training.

setOutputs(Matrix) - Method in class mklab.JGNN.adhoc.train.SampleClassification

Sets the label matrix of data samples, where each row corresponds to a different sample.

setParallelizedStochasticGradientDescent(boolean) - Method in class mklab.JGNN.adhoc.ModelTraining

Sets whether the training strategy should reflect stochastic gradient descent by randomly sampling from the training data samples.

setPatience(int) - Method in class mklab.JGNN.adhoc.ModelTraining

Sets the patience of the training strategy that performs early stopping.

setPrintOnImprovement(boolean) - Method in class mklab.JGNN.nn.loss.report.VerboseLoss

Changes by which criteria losses should be printed, that is, on every fixed count of epochs set by VerboseLoss.setInterval(int) or whenever the primary loss (the first one enclosed in the constructor) decreases.

setRange(double, double) - Method in class mklab.JGNN.core.distribution.Uniform

Sets the random of the uniform distribution.

setRowName(String) - Method in class mklab.JGNN.core.Matrix

Sets a name for the matrix's row dimension.

setSeed(long) - Method in class mklab.JGNN.core.distribution.Normal

setSeed(long) - Method in interface mklab.JGNN.core.Distribution

Sets the distribution's seed.

setSeed(long) - Method in class mklab.JGNN.core.distribution.Uniform

setStream(PrintStream) - Method in class mklab.JGNN.nn.loss.report.VerboseLoss

Changes where the output is printed.

setTo(Tensor) - Method in class mklab.JGNN.nn.inputs.Variable

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

Sets the Matrix to its asymmetrically normalized transformation by appropriately adjusting its element values.

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

L2-normalizes the tensor's elements.

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

Set all tensor element values to 1.

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

Divides the tensor's elements with their sum.

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

Set tensor elements to random values from the uniform range [0,1]

setToRandom(Distribution) - Method in class mklab.JGNN.core.Tensor

Set tensor elements to random values by sampling them from a given Distribution instance.

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

Sets the Matrix to its symmetrically normalized transformation by appropriately adjusting its element values.

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

Set all tensor element values to 1/Tensor.size()

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

Set all tensor element values to 0.

setTraining(boolean) - Method in class mklab.JGNN.nn.Model

Toggles the training mode of the model.

setTrainingSamples(Slice) - Method in class mklab.JGNN.adhoc.train.SampleClassification

Sets a slice of training samples.

setValidationLoss(Loss) - Method in class mklab.JGNN.adhoc.ModelTraining

Sets which Loss should be applied on validation data on each epoch.

setValidationSamples(Slice) - Method in class mklab.JGNN.adhoc.train.SampleClassification

Sets a slice of validation samples.

setValidationSplit(double) - Method in class mklab.JGNN.adhoc.train.AGFTraining

setValue(V) - Method in class mklab.JGNN.core.util.FastEntry

setVerbose(boolean) - Method in class mklab.JGNN.adhoc.ModelTraining

Deprecated.

This method was available in earlier JGNN versions but will be gradually phased out. Instead, wrap the validation loss within VerboseLoss to replicate the same behavior.

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

Sets a prototype matrix from which to borrow copying operations.

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

Sets a prototype matrix from which to borrow copying operations.

shuffle() - Method in class mklab.JGNN.core.Slice

Shuffles the slice.

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

Shuffles the slice with a provided randomization seed.

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

The sigmoid function 1/(1+exp(-x)).

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

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

Sigmoid - Class in mklab.JGNN.nn.activations

Implements a NNOperation that performs a sigmoid transformation of its single input.

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

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

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

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

Applies Loss.sigmoidDerivative(double) function.

SimpleNetwork - Class in primitives

Demonstrates custom initialization of parameters.

SimpleNetwork() - Constructor for class primitives.SimpleNetwork

size() - Method in class mklab.JGNN.adhoc.IdConverter

The number of registered identifiers.

size() - Method in class mklab.JGNN.core.Slice

Retrieves the size of the slice.

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

Slice - Class in mklab.JGNN.core

This class provices an interface with which to define data slices, for instance to sample labels.

Slice(Iterable<Long>) - Constructor for class mklab.JGNN.core.Slice

Instantiates a data slice from a collection of element identifiers.

SoftMax - Class in mklab.JGNN.nn.pooling

Implements a NNOperation that performs row-wise or column-wise softmax on vector tensors or matrices.

SoftMax() - Constructor for class mklab.JGNN.nn.pooling.SoftMax

SoftMax(boolean) - Constructor for class mklab.JGNN.nn.pooling.SoftMax

sort(Tensor, Matrix, long, long) - Method in class mklab.JGNN.nn.pooling.Sort

Sort - Class in mklab.JGNN.core.util

Sort - Class in mklab.JGNN.nn.pooling

Sort() - Constructor for class mklab.JGNN.core.util.Sort

Sort(int) - Constructor for class mklab.JGNN.nn.pooling.Sort

sortedIndexes(double[]) - Static method in class mklab.JGNN.core.util.Sort

sortedIndexes(ArrayList<Double>) - Static method in class mklab.JGNN.core.util.Sort

SortPooling - Class in graphClassification

SortPooling() - Constructor for class graphClassification.SortPooling

SortPoolingManual - Class in graphClassification

SortPoolingManual() - Constructor for class graphClassification.SortPoolingManual

Sparse2DIterator(Iterator<Long>) - Constructor for class mklab.JGNN.core.matrix.SparseMatrix.Sparse2DIterator

SparseMatrix - Class in mklab.JGNN.core.matrix

A sparse Matrix that allocates memory only for non-zero elements.

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

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

SparseMatrix.Sparse2DIterator - Class in mklab.JGNN.core.matrix

SparseSymmetric - Class in mklab.JGNN.core.matrix

Deprecated.

Under development.

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

Deprecated.

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

SparseTensor - Class in mklab.JGNN.core.tensor

This class provides a sparse Tensor with many zero elements.

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

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

SPECIES - Static variable in class mklab.JGNN.core.tensor.VectorizedTensor

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

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

Computes the square root of tensor elements.

startTape() - Method in class mklab.JGNN.nn.operations.LSTM

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

submit(Runnable) - Method in class mklab.JGNN.core.ThreadPool

Submits a runnable to be executed at some future point by a thread, for example via ThreadPool.getInstance().submit(new Runnable(){public void run(){...}});.

subtensorShouldAccessCorrectElements() - Method in class mklab.JGNN.core.TensorTest

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

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

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

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

Sum - Class in mklab.JGNN.nn.pooling

Implements a NNOperation that performs row-wise or column-wise sum reduction on vector tensors or matrices.

Sum() - Constructor for class mklab.JGNN.nn.pooling.Sum

Sum(boolean) - Constructor for class mklab.JGNN.nn.pooling.Sum

symmetricMatrixShouldWork() - Method in class mklab.JGNN.core.MatrixTest

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

Creates a copy of the Matrix that holds its symmetrically normalized version.

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