Crate concision_neural

Source
Expand description

The neural network abstractions used to create and train models.

This library provides a

Modules§

error
model
This module provides the scaffolding for creating models and layers in a neural network.
prelude
train
This module implements various training mechanisms for neural networks. Here, implemented trainers are lazily evaluated providing greater flexibility and performance.
traits
types
utils
Utilities for neural networks.

Structs§

Dropout
The Dropout layer is randomly zeroizes inputs with a given probability (p). This regularization technique is often used to prevent overfitting.
KeyValue
ModelFeatures
ModelParams
This object is an abstraction over the parameters of a deep neural network model. This is done to isolate the necessary parameters from the specific logic within a model allowing us to easily create additional stores for tracking velocities, gradients, and other metrics we may need.
StandardModelConfig
Trainer

Enums§

Hyperparameters
NeuralError

Traits§

Activate
BinaryAction
Model
This trait defines the base interface for all models, providing access to the models configuration, layout, and learned parameters.
NetworkConfig
TrainingConfiguration