Expand description
The neural network abstractions used to create and train models.
§Features
- Model: A trait for defining a neural network model.
- ModelParams: A structure for storing the parameters of a neural network model.
- StandardModelConfig: A standard configuration for the models
- Predict: A trait extending the basic Forward pass
- Train: A trait for training a neural network model.
§Work in Progress
- LayerBase: Functional wrappers for the ParamsBase structure.
Re-exports§
pub use super::Model;pub use super::config::*;pub use super::layout::*;pub use super::model_params::*;pub use super::trainer::*;
Modules§
- error
- layers
- This module implments various layers for a neural network
- model
- This module provides the scaffolding for creating models and layers in a neural network.
- prelude
- 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. - Hyperparameters
Iter - An iterator over the variants of Hyperparameters
- KeyValue
- Layer
Base
Enums§
Traits§
- Layer
- A layer within a neural-network containing a set of parameters and an activation function. Here, this manifests as a wrapper around the parameters of the layer with a generic activation function and corresponding traits to denote desired behaviors.
- Network
Config - Predict
- Predict isn’t designed to be implemented directly, rather, as a blanket impl for any
entity that implements the
Forwardtrait. This is primarily used to define the base functionality of theModeltrait. - Predict
With Confidence - This trait extends the
Predicttrait to include a confidence score for the prediction. The confidence score is calculated as the inverse of the variance of the output. - Train
- This trait defines the training process for the network
- Training
Configuration
Type Aliases§
- Neural
Result - a type alias for a Result with a NeuralError