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

T

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

The tanh activation (exp(x)-exp(-x))/(exp(x)+exp(-x))

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

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

Tanh - Class in mklab.JGNN.nn.activations

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

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

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

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

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

Applies Loss.tanhDerivative(double) function.

tapeError - Variable in class mklab.JGNN.nn.NNOperation.ThreadData

tensor - Variable in class mklab.JGNN.core.matrix.VectorizedMatrix

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

Tensor - Class in mklab.JGNN.core

This class provides a native java implementation of Tensor functionalities.

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

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

Construct that creates a tensor of zeros given its number of elements

TensorTest - Class in mklab.JGNN.core

TensorTest - Class in mklab.JGNN

TensorTest() - Constructor for class mklab.JGNN.core.TensorTest

TensorTest() - Constructor for class mklab.JGNN.TensorTest

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

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

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

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

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

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

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

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

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

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

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

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

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

testFiniteDerivative() - Method in class mklab.JGNN.core.util.LossTest

testFiniteLoss() - Method in class mklab.JGNN.core.util.LossTest

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

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

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

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

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

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

testLargeCrossEntropyDerivativeLabel() - Method in class mklab.JGNN.core.util.LossTest

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

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

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

testNegativeCrossEntropyDerivativeLabel() - Method in class mklab.JGNN.core.util.LossTest

testNegativeCrossEntropyDerivativePrediction() - Method in class mklab.JGNN.core.util.LossTest

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

testNonbinaryCrossEntropyDerivativeLabel() - Method in class mklab.JGNN.core.util.LossTest

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

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

testNumeric() - Method in class mklab.JGNN.TensorTest

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

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

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

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

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

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

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

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

testRange2D() - Method in class mklab.JGNN.core.MatrixTest

testRange2DOutOfBounds() - Method in class mklab.JGNN.core.MatrixTest

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

ThreadData() - Constructor for class mklab.JGNN.nn.NNOperation.ThreadData

ThreadPool - Class in mklab.JGNN.core

This class provides thread execution pool utilities while keeping track of thread identifiers for use by thread-specific NNOperation.

ThreadPool(int) - Constructor for class mklab.JGNN.core.ThreadPool

To - Class in mklab.JGNN.nn.operations

Implements a NNOperation that lists the second element of the 2D matrix element iterator.

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

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

Retrieves a representation of the Tensor as an array of doubles.

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

Creates a copy of the matrix organized as a dense matrix.

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

Converts a tensor of Tensor.size()==1 to double.

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

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

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

Creates a copy of the matrix organized as a sparse matrix.

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

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

A string serialization of the tensor that can be used by the constructor DenseTensor(String) to create an identical copy.

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

train(ModelTraining) - Method in class mklab.JGNN.nn.Model

Trains the model by calling ModelTraining.train(Model).

train(ModelTraining, Matrix, Matrix, Slice, Slice) - Method in class mklab.JGNN.nn.Model

Deprecated.

Training data have been moved inside ModelTraining instances to allow a uniform interface for all training scheme automations. Use Model.train(ModelTraining) instead.

train(Tensor[], Tensor) - Method in class mklab.JGNN.nn.operations.LSTM

train(Loss, Optimizer, List<Tensor>, List<Tensor>) - Method in class mklab.JGNN.nn.Model

Performs the training of #train(Optimizer, List, List, List) for unit weights.

train(Loss, Optimizer, List<Tensor>, List<Tensor>, List<Tensor>) - Method in class mklab.JGNN.nn.Model

Performs one parameter adjustment step (e.g.

train(Model) - Method in class mklab.JGNN.adhoc.ModelTraining

Trains the parameters of a Model based on current settings and the data.

train(Model, Matrix, Matrix, Slice, Slice) - Method in class mklab.JGNN.adhoc.ModelTraining

Deprecated.

This method's full implementation has been moved to ModelTraining.train(Model)

trainOnOutputError(Tensor[], Tensor) - Method in class mklab.JGNN.nn.operations.LSTM

trainParameters(Optimizer, Tensor) - Method in class mklab.JGNN.nn.inputs.Constant

trainParameters(Optimizer, Tensor) - Method in class mklab.JGNN.nn.inputs.Parameter

trainParameters(Optimizer, Tensor) - Method in class mklab.JGNN.nn.inputs.Variable

trainParameters(Optimizer, Tensor) - Method in class mklab.JGNN.nn.NNOperation

trainTowardsZero(Optimizer, List<Tensor>) - Method in class mklab.JGNN.nn.Model

Is equivalent to calling Model.train(Loss, Optimizer, List, List) for new Zero() loss.

TrajectoryData - Class in graphClassification

This class generates trajectory graph labels.

TrajectoryData(int) - Constructor for class graphClassification.TrajectoryData

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

Performs the linear algebra transformation A*x where A is this matrix and x a vector

Transpose - Class in mklab.JGNN.nn.operations

Implements a NNOperation that performs matrix transposition.

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

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

Creates a transposed copy of the matrix.

Transposed1DIterator(Iterator<Long>) - Constructor for class mklab.JGNN.core.matrix.TransposedMatrix.Transposed1DIterator

Transposed2DIterator(Iterator<Map.Entry<Long, Long>>) - Constructor for class mklab.JGNN.core.matrix.TransposedMatrix.Transposed2DIterator

TransposedMatrix - Class in mklab.JGNN.core.matrix

Generates a transposed version of a base matrix, with which it shares elements.

TransposedMatrix(Matrix) - Constructor for class mklab.JGNN.core.matrix.TransposedMatrix

TransposedMatrix.Transposed1DIterator - Class in mklab.JGNN.core.matrix

TransposedMatrix.Transposed2DIterator - Class in mklab.JGNN.core.matrix

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

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

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

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

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

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

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

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

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

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

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

Deprecated.

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

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

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

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

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

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

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

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

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

Retrieves positions within the tensor that may hold non-zero elements.

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

tutorial - package tutorial

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