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

M

main(String[]) - Static method in class Benchmarks

main(String[]) - Static method in class classification.LogisticRegression

main(String[]) - Static method in class classification.MLP

main(String[]) - Static method in class graphClassification.MeanPooling

main(String[]) - Static method in class graphClassification.MessageSortPooling

main(String[]) - Static method in class graphClassification.SortPooling

main(String[]) - Static method in class graphClassification.SortPoolingManual

main(String[]) - Static method in class nodeClassification.APPNP

main(String[]) - Static method in class nodeClassification.GAT

main(String[]) - Static method in class nodeClassification.GCN

main(String[]) - Static method in class nodeClassification.GCNII

main(String[]) - Static method in class nodeClassification.HetGCN

main(String[]) - Static method in class nodeClassification.MessagePassing

main(String[]) - Static method in class nodeClassification.Scripting

main(String[]) - Static method in class primitives.ModelBuilderInternals

main(String[]) - Static method in class primitives.SimpleNetwork

main(String[]) - Static method in class tutorial.Learning

main(String[]) - Static method in class tutorial.NN

main(String[]) - Static method in class tutorial.Quickstart

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

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

Performs the matrix multiplication of this*with and the recipient.

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

matmul(Matrix, boolean, boolean) - Method in class mklab.JGNN.core.matrix.DenseMatrix

matmul(Matrix, boolean, boolean) - Method in class mklab.JGNN.core.Matrix

Can be used to perform fast computation of the matrix multiplications
this*with,
this.transposed()*with
this*with.transposed(),
this.transposed()*with.transposed()
while avoiding the overhead of calling Matrix.transposed().

matmul(Matrix, boolean, boolean) - Method in class mklab.JGNN.core.matrix.VectorizedMatrix

MatMul - Class in mklab.JGNN.nn.operations

Implements a NNOperation that multiplies its two matrix inputs.

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

Matrix - Class in mklab.JGNN.core

This class provides an abstract implementation of Matrix functionalities.

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

MatrixTest - Class in mklab.JGNN.core

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

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

Computes the maximum tensor element.

Max - Class in mklab.JGNN.nn.pooling

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

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

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

Mean - Class in mklab.JGNN.nn.pooling

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

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

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

MeanPooling - Class in graphClassification

MeanPooling() - Constructor for class graphClassification.MeanPooling

Memory - Class in mklab.JGNN.core

A memory management system for thread-safe allocation and release of arrays of doubles.

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

Memory.Scope - Class in mklab.JGNN.core

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

MessagePassing - Class in nodeClassification

Demonstrates classification with a message passing architecture.

MessagePassing() - Constructor for class nodeClassification.MessagePassing

MessageSortPooling - Class in graphClassification

MessageSortPooling() - Constructor for class graphClassification.MessageSortPooling

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

Computes the minimum tensor element.

mklab.JGNN.adhoc - package mklab.JGNN.adhoc

Contains classes that simplify data loading, model building, and training.

mklab.JGNN.adhoc.datasets - package mklab.JGNN.adhoc.datasets

Contains datasets for out-of-the-box experimentation.

mklab.JGNN.adhoc.parsers - package mklab.JGNN.adhoc.parsers

Contains model builders that parse expression of the Neuralang scripting language to simplify mathematical parts of the definitions.

mklab.JGNN.adhoc.train - package mklab.JGNN.adhoc.train

Contains model training strategies that correspond to different predictive tasks.

mklab.JGNN.core - package mklab.JGNN.core

Contains base numerical data classes, as well as supporting abstract classes.

mklab.JGNN.core.distribution - package mklab.JGNN.core.distribution

Contains data distributions that produce one numerical value and can be used for tensor value initialization.

mklab.JGNN.core.empty - package mklab.JGNN.core.empty

Contains empty extensions of datatypes that hold only dimension names and sizes but no ddata.

mklab.JGNN.core.matrix - package mklab.JGNN.core.matrix

Contains implementations of matrix classes, of transparent access to parts of these classes, and of column/row repetitions that broadcast vectors into matrices.

mklab.JGNN.core.tensor - package mklab.JGNN.core.tensor

Contains implementations of tensor classes, as well as transparent access to parts of these classes.

mklab.JGNN.core.util - package mklab.JGNN.core.util

Contains utility functions that are employed internally, mainly optimized 1D and 2D iterators.

mklab.JGNN.nn - package mklab.JGNN.nn

Implements neural networks components that are combined to define GNNs or other types of machine learning models.

mklab.JGNN.nn.activations - package mklab.JGNN.nn.activations

Implements activations function to be used as model operations.

mklab.JGNN.nn.initializers - package mklab.JGNN.nn.initializers

Implements initializers to be applied on Model parameters to stochastically induce some desired property at the first training epoch.

mklab.JGNN.nn.inputs - package mklab.JGNN.nn.inputs

Contains various types of neural architecture inputs.

mklab.JGNN.nn.loss - package mklab.JGNN.nn.loss

Contains classes for instantiating loss function.

mklab.JGNN.nn.loss.report - package mklab.JGNN.nn.loss.report

Contains losses that wrap other losses and augment their numeric computations with live reporting of the training status.

mklab.JGNN.nn.operations - package mklab.JGNN.nn.operations

Contains popular neural network and GNN operations.

mklab.JGNN.nn.optimizers - package mklab.JGNN.nn.optimizers

Contains optimizers that can be used to update training losses.

mklab.JGNN.nn.pooling - package mklab.JGNN.nn.pooling

Contains pooling/reduction operations that reduce the dimensions of inputs.

MLP - Class in classification

Demonstrates classification with a two-layer perceptron

MLP() - Constructor for class classification.MLP

Model - Class in mklab.JGNN.nn

This class is a way to organize NNOperation trees into trainable machine learning models.

Model() - Constructor for class mklab.JGNN.nn.Model

Deprecated.

Prefer using model builders for symbolic model definitions.

ModelBuilder - Class in mklab.JGNN.adhoc

This class and subclasses can be used to create Model instances by automatically creating and managing NNOperation instances based on textual descriptions.

ModelBuilder() - Constructor for class mklab.JGNN.adhoc.ModelBuilder

ModelBuilder(Model) - Constructor for class mklab.JGNN.adhoc.ModelBuilder

ModelBuilderInternals - Class in primitives

Demonstrates model builder internal node access that allows training with a symbolically defined loss function.

ModelBuilderInternals() - Constructor for class primitives.ModelBuilderInternals

ModelTraining - Class in mklab.JGNN.adhoc

This is a helper class that automates the definition of training processes of Model instances by defining the number of epochs, loss functions, number of batches and the ability to use ThreadPool for parallelized batch computations.

ModelTraining() - Constructor for class mklab.JGNN.adhoc.ModelTraining

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

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

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

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

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

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

Multiply - Class in mklab.JGNN.nn.operations

Implements a NNOperation that multiplies its two inputs element-by-element.

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

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