Autoencoder

Eseguire l'apprendimento senza supervisione delle feature utilizzando reti neurali autoencoder

Se si dispone di dati non etichettati, eseguire l’apprendimento senza supervisione con reti neurali autoencoder per l’estrazione di feature.

Classi

Autoencoder Autoencoder class

`trainAutoencoder`	Train an autoencoder
`trainSoftmaxLayer`	Train a softmax layer for classification

`decode`	Decode encoded data
`encode`	Encode input data
`generateFunction`	Generate a MATLAB function to run the autoencoder
`generateSimulink`	Generate a Simulink model for the autoencoder
`network`	Convert `Autoencoder` object into `network` object
`plotWeights`	Plot a visualization of the weights for the encoder of an autoencoder
`predict`	Reconstruct the inputs using trained autoencoder
`stack`	Stack encoders from several autoencoders together
`view`	View autoencoder

Train Stacked Autoencoders for Image Classification
This example shows how to train stacked autoencoders to classify images of digits.