Uses of Interface
org.tribuo.math.la.Tensor

Packages that use Tensor

Package	Description
org.tribuo.classification.sgd.crf	Provides an implementation of a linear chain CRF trained using Stochastic Gradient Descent.
org.tribuo.math	Contains the implementation of Tribuo's math library, it's gradient descent optimisers, kernels and a set of math related utils.
org.tribuo.math.la	Provides a linear algebra system used for numerical operations in Tribuo.
org.tribuo.math.optimisers	Provides implementations of StochasticGradientOptimiser.
org.tribuo.math.optimisers.util	Provides some utility tensors for use in gradient optimisers.

Uses of Tensor in org.tribuo.classification.sgd.crf

Methods in org.tribuo.classification.sgd.crf that return Tensor

Modifier and Type	Method and Description
Tensor[]	CRFParameters.get()
Tensor[]	CRFParameters.getEmptyCopy() Returns a 3 element Tensor array.
Tensor[]	CRFParameters.merge(Tensor[][] gradients, int size)

Methods in org.tribuo.classification.sgd.crf with parameters of type Tensor

Modifier and Type	Method and Description
Tensor[]	CRFParameters.merge(Tensor[][] gradients, int size)
void	CRFParameters.set(Tensor[] newWeights)
void	CRFParameters.update(Tensor[] gradients)

Uses of Tensor in org.tribuo.math

Methods in org.tribuo.math that return Tensor

Modifier and Type	Method and Description
Tensor[]	Parameters.get() Get a reference to the underlying Tensor array.
Tensor[]	LinearParameters.get()
Tensor[]	Parameters.getEmptyCopy() Generates an empty copy of the underlying Tensor array.
Tensor[]	LinearParameters.getEmptyCopy() This returns a DenseMatrix the same size as the Parameters.
Tensor[]	LinearParameters.gradients(com.oracle.labs.mlrg.olcut.util.Pair<Double,SGDVector> score, SGDVector features) Generate the gradients for a particular feature vector given the loss and the per output gradients.
Tensor[]	FeedForwardParameters.gradients(com.oracle.labs.mlrg.olcut.util.Pair<Double,SGDVector> score, SGDVector features) Generates the parameter gradients given the loss, output gradient and input features.
Tensor[]	Parameters.merge(Tensor[][] gradients, int size) Merge together an array of gradient arrays.
Tensor[]	LinearParameters.merge(Tensor[][] gradients, int size)
Tensor[]	StochasticGradientOptimiser.step(Tensor[] updates, double weight) Take a Tensor array of gradients and transform them according to the current weight and learning rates.

Methods in org.tribuo.math with parameters of type Tensor

Modifier and Type	Method and Description
Tensor[]	Parameters.merge(Tensor[][] gradients, int size) Merge together an array of gradient arrays.
Tensor[]	LinearParameters.merge(Tensor[][] gradients, int size)
void	Parameters.set(Tensor[] newWeights) Set the underlying Tensor array to newWeights.
void	LinearParameters.set(Tensor[] newWeights)
Tensor[]	StochasticGradientOptimiser.step(Tensor[] updates, double weight) Take a Tensor array of gradients and transform them according to the current weight and learning rates.
void	Parameters.update(Tensor[] gradients) Apply gradients to the parameters.
void	LinearParameters.update(Tensor[] gradients)

Uses of Tensor in org.tribuo.math.la

Subinterfaces of Tensor in org.tribuo.math.la

Modifier and Type	Interface and Description
interface	Matrix Interface for 2 dimensional Tensors.
interface	SGDVector Interface for 1 dimensional Tensors.

Classes in org.tribuo.math.la that implement Tensor

Modifier and Type	Class and Description
class	DenseMatrix A dense matrix, backed by a primitive array.
class	DenseSparseMatrix A matrix which is dense in the first dimension and sparse in the second.
class	DenseVector A dense vector, backed by a double array.
class	SparseVector A sparse vector.

Methods in org.tribuo.math.la that return Tensor

Modifier and Type	Method and Description
Tensor	Tensor.reshape(int[] shape) Reshapes the Tensor to the supplied shape.
Tensor	SparseVector.reshape(int[] newShape)
Tensor	DenseVector.reshape(int[] newShape)
Tensor	DenseSparseMatrix.reshape(int[] newShape)
Tensor	DenseMatrix.reshape(int[] newShape)

Methods in org.tribuo.math.la with parameters of type Tensor

Modifier and Type	Method and Description
default void	Tensor.hadamardProductInPlace(Tensor other) Same as hadamardProductInPlace(org.tribuo.math.la.Tensor, java.util.function.DoubleUnaryOperator), but applies the identity function.
void	Tensor.hadamardProductInPlace(Tensor other, DoubleUnaryOperator f) Updates this Tensor with the Hadamard product (i.e., a term by term multiply) of this and other.
void	SparseVector.hadamardProductInPlace(Tensor other, DoubleUnaryOperator f)
void	DenseVector.hadamardProductInPlace(Tensor other, DoubleUnaryOperator f)
void	DenseSparseMatrix.hadamardProductInPlace(Tensor other, DoubleUnaryOperator f) Only implemented for DenseMatrix.
void	DenseMatrix.hadamardProductInPlace(Tensor other, DoubleUnaryOperator f)
default void	Tensor.intersectAndAddInPlace(Tensor other) Same as intersectAndAddInPlace(org.tribuo.math.la.Tensor, java.util.function.DoubleUnaryOperator), but applies the identity function.
void	Tensor.intersectAndAddInPlace(Tensor other, DoubleUnaryOperator f) Updates this Tensor by adding all the values from the intersection with other.
void	SparseVector.intersectAndAddInPlace(Tensor other, DoubleUnaryOperator f)
void	DenseVector.intersectAndAddInPlace(Tensor other, DoubleUnaryOperator f)
void	DenseSparseMatrix.intersectAndAddInPlace(Tensor other, DoubleUnaryOperator f) Only implemented for DenseMatrix.
void	DenseMatrix.intersectAndAddInPlace(Tensor other, DoubleUnaryOperator f)
static boolean	Tensor.shapeCheck(Tensor first, Tensor second)

Uses of Tensor in org.tribuo.math.optimisers

Methods in org.tribuo.math.optimisers that return Tensor

Modifier and Type	Method and Description
Tensor[]	SGD.step(Tensor[] updates, double weight)
Tensor[]	RMSProp.step(Tensor[] updates, double weight)
Tensor[]	Pegasos.step(Tensor[] updates, double weight)
Tensor[]	ParameterAveraging.step(Tensor[] updates, double weight) This passes the gradient update to the inner optimiser, then updates the average weight values.
Tensor[]	Adam.step(Tensor[] updates, double weight)
Tensor[]	AdaGradRDA.step(Tensor[] updates, double weight)
Tensor[]	AdaGrad.step(Tensor[] updates, double weight)
Tensor[]	AdaDelta.step(Tensor[] updates, double weight)

Methods in org.tribuo.math.optimisers with parameters of type Tensor

Modifier and Type	Method and Description
Tensor[]	SGD.step(Tensor[] updates, double weight)
Tensor[]	RMSProp.step(Tensor[] updates, double weight)
Tensor[]	Pegasos.step(Tensor[] updates, double weight)
Tensor[]	ParameterAveraging.step(Tensor[] updates, double weight) This passes the gradient update to the inner optimiser, then updates the average weight values.
Tensor[]	Adam.step(Tensor[] updates, double weight)
Tensor[]	AdaGradRDA.step(Tensor[] updates, double weight)
Tensor[]	AdaGrad.step(Tensor[] updates, double weight)
Tensor[]	AdaDelta.step(Tensor[] updates, double weight)

Uses of Tensor in org.tribuo.math.optimisers.util

Classes in org.tribuo.math.optimisers.util that implement Tensor

Modifier and Type	Class and Description
class	ShrinkingMatrix A subclass of DenseMatrix which shrinks the value every time a new value is added.
class	ShrinkingVector A subclass of DenseVector which shrinks the value every time a new value is added.

Methods in org.tribuo.math.optimisers.util that return Tensor

Modifier and Type	Method and Description
Tensor	ShrinkingTensor.convertToDense()

Methods in org.tribuo.math.optimisers.util with parameters of type Tensor

Modifier and Type	Method and Description
void	ShrinkingVector.intersectAndAddInPlace(Tensor other, DoubleUnaryOperator f)
void	ShrinkingMatrix.intersectAndAddInPlace(Tensor other, DoubleUnaryOperator f)