All Packages
Package Summary
Package
Description
Contains classes that simplify data loading, model building, and training.
Contains datasets for out-of-the-box experimentation.
Contains model builders that parse expression of the Neuralang scripting
language to simplify mathematical parts of the definitions.
Contains model training strategies that correspond to different predictive
tasks.
Contains base numerical data classes, as well as supporting abstract classes.
Contains data distributions that produce one numerical value and can be used
for tensor value initialization.
Contains empty extensions of datatypes that hold only dimension names and
sizes but no ddata.
Contains implementations of matrix classes, of transparent access to parts of
these classes, and of column/row repetitions that broadcast vectors into
matrices.
Contains implementations of tensor classes, as well as transparent access to
parts of these classes.
Contains utility functions that are employed internally, mainly optimized 1D
and 2D iterators.
Implements neural networks components that are combined to define GNNs or
other types of machine learning models.
Implements activations function to be used as model operations.
Implements initializers to be applied on
Model
parameters to stochastically induce some desired property at the first
training epoch.Contains various types of neural architecture inputs.
Contains classes for instantiating loss function.
Contains losses that wrap other losses and augment their numeric computations
with live reporting of the training status.
Contains popular neural network and GNN operations.
Contains optimizers that can be used to update training losses.
Contains pooling/reduction operations that reduce the dimensions of inputs.