Module `light_labyrinth.hyperparams`

The light_labyrinth.hyperparams module includes all the necessary hyperparameter classes to build a custom Light Labyrinth model.

Using a proper error function or adding a regularization term may significantly improve the model's performance. This module provides various hyperparameters the user can exploit instead of the default ones, predefined in the models.

Expand source code

"""
The `light_labyrinth.hyperparams` module includes all the
necessary hyperparameter classes to build a custom Light Labyrinth model.

Using a proper error function or adding a regularization term may 
significantly improve the model's performance. This module provides 
various hyperparameters the user can exploit instead of the default ones, 
predefined in the models.
"""

Sub-modules

light_labyrinth.hyperparams.activation: The light_labyrinth.hyperparams.activation module includes ReflectiveIndex classes with predefined splitting criteria (or activation functions) …
light_labyrinth.hyperparams.error_function: The light_labyrinth.hyperparams.error_function module includes ErrorCalculator classes with predefined error functions (or loss functions) that …
light_labyrinth.hyperparams.optimization: The light_labyrinth.hyperparams.optimization module includes Optimizer classes with predefined optimization algorithms that can be used for …
light_labyrinth.hyperparams.regularization: The light_labyrinth.hyperparams.regularization module includes Regularization classes that can be used for training Light Labyrinth models. The …
light_labyrinth.hyperparams.weights_init: The light_labyrinth.hyperparams.weights_init module includes WeightsInit class that allows to initialize model's weights before training.