Autoencoder Class

Superclasses:

(To be removed) Autoencoder class

Autoencoder will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Description

An Autoencoder object contains an autoencoder network, which consists of an encoder and a decoder. The encoder maps the input to a hidden representation. The decoder attempts to map this representation back to the original input.

Construction

autoenc = trainAutoencoder(X) returns an autoencoder trained using the training data in X.

autoenc = trainAutoencoder(X,hiddenSize) returns an autoencoder with the hidden representation size of hiddenSize.

autoenc = trainAutoencoder(___,Name,Value) returns an autoencoder for any of the above input arguments with additional options specified by one or more name-value pair arguments.

Input Arguments

X — Training data

matrix | cell array of image data

Training data, specified as a matrix of training samples or a cell array of image data. If X is a matrix, then each column contains a single sample. If X is a cell array of image data, then the data in each cell must have the same number of dimensions. The image data can be pixel intensity data for gray images, in which case, each cell contains an m-by-n matrix. Alternatively, the image data can be RGB data, in which case, each cell contains an m-by-n-3 matrix.

Data Types: single | double | cell

hiddenSize — Size of hidden representation of the autoencoder

10 (default) | positive integer value

Size of hidden representation of the autoencoder, specified as a positive integer value. This number is the number of neurons in the hidden layer.

Data Types: single | double

Properties

HiddenSize — Size of the hidden representation

a positive integer value

Size of the hidden representation in the hidden layer of the autoencoder, stored as a positive integer value.

Data Types: double

EncoderTransferFunction — Name of the transfer function for the encoder

string

Name of the transfer function for the encoder, stored as a string.

Data Types: char

EncoderWeights — Weights for the encoder

matrix

Weights for the encoder, stored as a matrix.

Data Types: double

EncoderBiases — Bias values for the encoder

vector

Bias values for the encoder, stored as a vector.

Data Types: double

DecoderTransferFunction — Name of the transfer function for the decoder

string

Name of the transfer function for the decoder, stored as a string.

Data Types: char

DecoderWeights — Weights for the decoder

matrix

Weights for the decoder, stored as a matrix.

Data Types: double

DecoderBiases — Bias values for the decoder

vector

Bias values for the decoder, stored as a vector.

Data Types: double

TrainingParameters — Parameters that trainAutoencoder uses for training the autoencoder

structure

Parameters that trainAutoencoder uses for training the autoencoder, stored as a structure.

Data Types: struct

ScaleData — Indicator for data that is rescaled

true or 1 (default) | false or 0

Indicator for data that is rescaled while passing to the autoencoder, stored as either true or false.

Autoencoders attempt to replicate their input at their output. For it to be possible, the range of the input data must match the range of the transfer function for the decoder. trainAutoencoder automatically scales the training data to this range when training an autoencoder. If the data was scaled while training an autoencoder, the predict, encode, and decode methods also scale the data.

Data Types: logical

Methods

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

Copy Semantics

Value. To learn how value classes affect copy operations, see Copying Objects.

Version History

Introduced in R2015b

R2026a: Autoencoder will be removed

Autoencoder will be removed in a future release.

To learn more about autoencoder workflows, see these examples and topics:

• Build Networks with Deep Network Designer

• Time Series Anomaly Detection Using Deep Learning

• Detect Anomalies Using Wavelet Scattering with Autoencoders

• Train Variational Autoencoder (VAE) to Generate Images

• List of Deep Learning Layer Blocks and Subsystems

• Code Generation for Deep Learning Networks

Train an autoencoder using the trainnet function or a custom training loop.

To design and customize your own neural network for these workflows, you can create a network using an array of deep learning layers or a dlnetwork object. To create and edit neural networks interactively and generate code, use the Deep Network Designer app. For a list of layers, see List of Deep Learning Layers.

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.