generateSimulink

Class: Autoencoder

Generate a Simulink model for the autoencoder

expand all in page

Syntax

generateSimulink(autoenc)

Description

generateSimulink(autoenc) creates a Simulink^® model for the autoencoder, autoenc.

example

Input Arguments

expand all

`autoenc` — Trained autoencoder
`Autoencoder` object

Trained autoencoder, returned as an object of the Autoencoder class.

Examples

expand all

Generate Simulink Model for Autoencoder

Load the training data.

X = digitSmallCellArrayData;

The training data is a 1-by-500 cell array, where each cell containing a 28-by-28 matrix representing a synthetic image of a handwritten digit.

Train an autoencoder with a hidden layer containing 25 neurons.

hiddenSize = 25;
autoenc = trainAutoencoder(X,hiddenSize,...
        'L2WeightRegularization',0.004,...
        'SparsityRegularization',4,...
        'SparsityProportion',0.15);

Create a Simulink model for the autoencoder, autoenc.

generateSimulink(autoenc)

Simulink model. The model passes constant x1 to a the autoencoder block. The autoencoder block passes its output to a scope block y1.

Version History

Introduced in R2015b