Crate concision_neural

concision-neural (cnc::neural)

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.

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.

HyperparametersIter

An iterator over the variants of Hyperparameters

KeyValue

LayerBase

ModelFeatures

The ModelFeatures provides 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.

ModelParamsBase

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

TrainingError

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.

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 the features method which aptly returns a copy of its ModelFeatures object.

ModelExt

ModelLayout

NetworkConfig

Predict

Predict isn’t designed to be implemented directly, rather, as a blanket impl for any entity that implements the Forward trait. This is primarily used to define the base functionality of the Model trait.

PredictWithConfidence

This trait extends the Predict trait 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

TrainingConfiguration

Type Aliases

ModelParams

NeuralResult

a type alias for a Result with a NeuralError