C# Class numl.Supervised.NeuralNetwork.Encoders.AutoencoderGenerator

An Autoencoding Network Generator.

By default this works as a (linear) denoising autoencoder. If the features used are within [0, 1] range then try specifying a different Output Function such as Logistic or Tanh.

Inheritance: NeuralNetworkGenerator, ISequenceGenerator

Show file Open project: sethjuarez/numl Class Usage Examples

Public Methods

Method	Description
AutoencoderGenerator ( ) : System	Instantiates a new Autoencoder Generator object.
Generate ( Matrix X, Vector y ) : IModel	Generates and returns a new Autoencoder model.
Generate ( Matrix X, Matrix Y ) : ISequenceModel

Method Details

AutoencoderGenerator() public method

Instantiates a new Autoencoder Generator object.

public AutoencoderGenerator ( ) : System
return	System

Generate() public method

Generates and returns a new Autoencoder model.

public Generate ( Matrix X, Vector y ) : IModel
X	Matrix	The Matrix to process.
y	numl.Math.LinearAlgebra.Vector	The original training label Vector (ignored).
return	IModel

Generate() public method

public Generate ( Matrix X, Matrix Y ) : ISequenceModel
X	Matrix
Y	Matrix
return	ISequenceModel