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
- Model
Features - Model
Params - 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.
- Standard
Model Config - Trainer
Enums§
Traits§
- Activate
- Binary
Action - Model
- This trait defines the base interface for all models, providing access to the models configuration, layout, and learned parameters.
- Network
Config - Training
Configuration