Crate concision_neural

concision-neural

This crate focuses on implementing various neural network components, including models, layers, and training mechanisms.

Overview

Neural networks are a fundamental part of machine learning, and this crate provides a comprehensive set of tools to build, configure, and train neural network models. Listed below are several key components of the crate:

• Model: A trait for defining a neural network model.
• ModelParamsBase: A dedicated object capable of storing the parameters for both shallow and deep neural networks.
• StandardModelConfig: A standard configuration for the models

Traits

This crate extends the Forward and Backward traits from the core crate to provide additional functionality for neural networks.

• Predict: A more robust implementation of the [Forward] trait
• Train: A trait for training a neural network model.

Modules

config

error

this module defines the NeuralError type, used to define the various errors encountered by the different components of a neural network. Additionally, the NeuralResult alias is defined for convenience, allowing for a more ergonomic way to handle results that may fail.

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.

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

The KeyValue type is used to generically represent a simple key-value pair within a store.

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

The ModelParamsBase object 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 as DeepModelParams or ShallowModelParams or 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.

StandardModelConfig

Trainer

Enums

HyperParams

Hyperparameters

Auto-generated discriminant enum variants

NeuralError

The NeuralError type is used to define the various errors encountered by the different components of a neural network. It is designed to be comprehensive, covering a wide range of potential issues that may arise during the operation of neural network components, such as invalid configurations, training failures, and other runtime errors. This error type is intended to provide a clear and consistent way to handle errors across the neural network components, making it easier to debug and resolve issues that may occur during the development and execution of neural network models.

TrainingError

Traits

DeepNeuralNetwork

The DeepNeuralNetwork trait is a specialization of the Model trait that provides additional functionality for deep neural networks. This trait is

DeepNeuralStore

The DeepNeuralStore trait for deep neural networks

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

ModelTrainer

NetworkConfig

The NetworkConfig trait extends the RawConfig trait to provide a more robust interface for neural network configurations.

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.

RawConfig

The RawConfig trait defines a basic interface for all configurations used within the framework for neural networks, their layers, and more.

RawHidden

The RawHidden trait for compatible representations of hidden layers

ShallowNeuralStore

The ShallowNeuralStore trait for shallow neural networks

Train

This trait defines the training process for the network

TrainingConfiguration

Type Aliases

DeepModelParams

a type alias for an owned representation of the DeepParamsBase generic of type A and the dimension D.

DeepParamsBase

a type alias for a deep representation of the ModelParamsBase using a vector of parameters as the hidden layers.

NeuralResult

a type alias for a Result configured to use the NeuralError implementation as its error type.

ShallowModelParams

a type alias for an owned representation of the DeepParamsBase generic of type A and the dimension D.

ShallowParamsBase

a type alias for a shallow representation of the ModelParamsBase using a single ParamsBase instance as the hidden layer.