Package mklab.JGNN.nn

package mklab.JGNN.nn

Implements neural networks components that are combined to define GNNs or other types of machine learning models. Hand-wiring everything may be cumbersome, so prefer using ModelBuilder and its extensions to construct Model instances. Components matching common neural operations are provided in sub-packages, where they are separated by their functional role as activations, inputs, operations, or pooling functions. In addition to operations. Additionally, Java code components are provided for losses and model parameter initialization.

Author:

Emmanouil Krasanakis

Related Packages

Package	Description
mklab.JGNN
mklab.JGNN.nn.activations	Implements activations function to be used as model operations.
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	Contains various types of neural architecture inputs.
mklab.JGNN.nn.loss	Contains classes for instantiating loss function.
mklab.JGNN.nn.operations	Contains popular neural network and GNN operations.
mklab.JGNN.nn.optimizers	Contains optimizers that can be used to update training losses.
mklab.JGNN.nn.pooling	Contains pooling/reduction operations that reduce the dimensions of inputs.

Class	Description
Initializer	This class defines an abstract interface for applying initializers to models.
Loss	This class provides an abstract implementation of loss functions to be used during Model training.
Model	This class is a way to organize NNOperation trees into trainable machine learning models.
NNOperation	This class defines an abstract neural network operation with forward and backpropagation capabilities.
NNOperation.ThreadData
Optimizer	Provides an interface for training tensors.