Expand description
This module provides the scaffolding for creating models and layers in a neural network.
Modules§
Structs§
- Model
Features - The
ModelFeaturesprovides a common way of defining the layout of a model. This is used to define the number of input features, the number of hidden layers, the number of hidden features, and the number of output features. - Model
Params Base - The
ModelParamsBaseobject is a generic ocntainer for storing the parameters of a neural network, regardless of the layout (e.g. shallow or deep). This is made possible through the introduction of a generic hidden layer type,H, that allows us to define aliases and additional traits for contraining the hidden layer type. That being said, we don’t reccoment using this type directly, but rather use the provided type aliases such asDeepModelParamsorShallowModelParamsor their owned variants. These provide a much more straighforward interface for typing the parameters of a neural network. We aren’t too worried about the transumtation between the two since users desiring this ability should simply stick with a deep representation, initializing only a single layer within the respective container. - Trainer
Traits§
- Deep
Neural Network - The
DeepNeuralNetworktrait is a specialization of theModeltrait that provides additional functionality for deep neural networks. This trait is - Model
- The base interface for all models; each model provides access to a configuration object
defined as the associated type
Config. The configuration object is used to provide hyperparameters and other control related parameters. In addition, the model’s layout is defined by thefeaturesmethod which aptly returns a copy of its [ModelFeatures] object. - Model
Ext - Model
Layout - Model
Trainer
Type Aliases§
- Deep
Model Params - a type alias for an owned representation of the
DeepParamsBasegeneric of typeAand the dimensionD. - Deep
Params Base - a type alias for a deep representation of the
ModelParamsBaseusing a vector of parameters as the hidden layers. - Shallow
Model Params - a type alias for an owned representation of the
DeepParamsBasegeneric of typeAand the dimensionD. - Shallow
Params Base - a type alias for a shallow representation of the
ModelParamsBaseusing a singleParamsBaseinstance as the hidden layer.