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

C

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

cast(Class<Type>) - Method in class mklab.JGNN.core.Tensor

Performs the equivalent of Java's typecasting that fits in functional interfaces.

CategoricalCrossEntropy - Class in mklab.JGNN.nn.loss

Implements a categorical cross-entropy Loss.
For binary classification of one output use BinaryCrossEntropy.

CategoricalCrossEntropy() - Constructor for class mklab.JGNN.nn.loss.CategoricalCrossEntropy

Initializes categorical cross entropy with 1.E-12 epsilon value.

CategoricalCrossEntropy(double) - Constructor for class mklab.JGNN.nn.loss.CategoricalCrossEntropy

Initializes categorical cross entropy with and epsilon value to bound its outputs in the range [log(epsilon), -log(epsilon)] instead of (-inf, inf).

Citeseer - Class in mklab.JGNN.adhoc.datasets

Downloads and constructs the Citeseer node classification Dataset.

Citeseer() - Constructor for class mklab.JGNN.adhoc.datasets.Citeseer

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

Retrieves a converter that maps class names to label dimentions.

classification - package classification

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

Adds a classification layer that gather the number of inputs nodes and applies softmax on all of them.

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

column - Variable in class mklab.JGNN.core.matrix.ColumnRepetition

ColumnRepetition - Class in mklab.JGNN.core.matrix

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

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

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

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

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

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

Complement - Class in mklab.JGNN.nn.operations

Implements a NNOperation that performs the operation 1-x for its simple input x.

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

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

Concatenates horizontally the output of a number of given layers, starting from the last one and going backwards.

concat(int) - Method in class mklab.JGNN.adhoc.parsers.LayeredBuilder

Concatenates horizontally the output of a number of given layers, starting from the last one and going backwards.

Concat - Class in mklab.JGNN.nn.operations

Implements a NNOperation that concatenates its two matrix inputs.

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

config(String, double) - Method in class mklab.JGNN.adhoc.ModelBuilder

Declares a configuration hyperparameter, which can be used to declare matrix and vector parameters during ModelBuilder.operation(String) expressions.

config(String, double) - Method in class mklab.JGNN.adhoc.parsers.FastBuilder

config(String, double) - Method in class mklab.JGNN.adhoc.parsers.LayeredBuilder

config(String, double) - Method in class mklab.JGNN.adhoc.parsers.Neuralang

config(String, String) - Method in class mklab.JGNN.adhoc.ModelBuilder

Applies ModelBuilder.config(String, double) where the set value is obtained from another configuration hyperaparameter.

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

configFrom(ModelBuilder) - Method in class mklab.JGNN.adhoc.ModelTraining

Retrieves the learning rate (lr), epochs, batches, and patience parameters from the configurations of a

constant(String, double) - Method in class mklab.JGNN.adhoc.ModelBuilder

Declares a non-learnable constant component with the given name.

constant(String, double) - Method in class mklab.JGNN.adhoc.parsers.FastBuilder

constant(String, double) - Method in class mklab.JGNN.adhoc.parsers.LayeredBuilder

constant(String, double) - Method in class mklab.JGNN.adhoc.parsers.Neuralang

constant(String, Tensor) - Method in class mklab.JGNN.adhoc.ModelBuilder

Declares a non-learnable constant component with the given name.

constant(String, Tensor) - Method in class mklab.JGNN.adhoc.parsers.FastBuilder

constant(String, Tensor) - Method in class mklab.JGNN.adhoc.parsers.LayeredBuilder

constant(String, Tensor) - Method in class mklab.JGNN.adhoc.parsers.Neuralang

Constant - Class in mklab.JGNN.nn.inputs

Implements a NNOperation that holds a constant tensor.

Constant(Tensor) - Constructor for class mklab.JGNN.nn.inputs.Constant

Creates a constant holding a tensor.

contains(Object) - Method in class mklab.JGNN.adhoc.IdConverter

Checks whether the object has been registered with IdConverter.getOrCreateId(Object).

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

Creates a Tensor.zeroCopy() and transfers to it all potentially non-zero element values.

Cora - Class in mklab.JGNN.adhoc.datasets

Downloads and constructs the Cora node classification Dataset.

Cora() - Constructor for class mklab.JGNN.adhoc.datasets.Cora

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

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

createForwardValidity(List<Tensor>) - Method in class mklab.JGNN.adhoc.ModelBuilder

Asserts that a forward run of the architecture is valid given some input data.

createGraphs(int) - Method in class graphClassification.TrajectoryData

createTimeAdjacency(int) - Method in class graphClassification.TrajectoryData

createTrajectory(int) - Method in class graphClassification.TrajectoryData

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

A cross entropy loss for one sample computes as -label*log(output) -(1-label)*log(1-output).

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

The derivative of the Loss.crossEntropy(double, double) loss.

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

The derivative of the #crossEntropyCategorical(double, double) loss.

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

The derivative of crossEntropy(sigmoid(x), label) with respect to x.

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

The derivative of crossEntropy(tanh(x), label) with respect to x.

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