decode

Class: Autoencoder

Decode encoded data

expand all in page

Syntax

Y = decode(autoenc,Z)

Description

Y = decode(autoenc,Z)returns the decoded data Y, using the autoencoder autoenc.

example

Input Arguments

expand all

`autoenc` — Trained autoencoder
`Autoencoder` object

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

`Z` — Data encoded by `autoenc`
matrix

Data encoded by autoenc, specified as a matrix. Each column of Z represents an encoded sample (observation).

Data Types: single | double

Output Arguments

expand all

`Y` — Decoded data
matrix | cell array of image data

Decoded data, returned as a matrix or a cell array of image data.

If the autoencoder autoenc was trained on a cell array of image data, then Y is also a cell array of images.

If the autoencoder autoenc was trained on a matrix, then Y is also a matrix, where each column of Y corresponds to one sample or observation.

Examples

expand all

Decode Encoded Data For New Images

Open Script

Load the training data.

X = digitTrainCellArrayData;

X is a 1-by-5000 cell array, where each cell contains a 28-by-28 matrix representing a synthetic image of a handwritten digit.

Train an autoencoder using the training data with a hidden size of 15.

hiddenSize = 15;
autoenc = trainAutoencoder(X,hiddenSize);

Extract the encoded data for new images using the autoencoder.

Xnew = digitTestCellArrayData;
features = encode(autoenc,Xnew);

Decode the encoded data from the autoencoder.

Y = decode(autoenc,features);

Y is a 1-by-5000 cell array, where each cell contains a 28-by-28 matrix representing a synthetic image of a handwritten digit.

Algorithms

If the input to an autoencoder is a vector $x \in ℝ^{D_{x}}$ , then the encoder maps the vector x to another vector $z \in ℝ^{D^{(1)}}$ as follows:

$z = h^{^{(1)}} (W^{(1)} x + b^{(1)}),$

where the superscript (1) indicates the first layer. $h^{(1)} : ℝ^{D^{(1)}} \to ℝ^{D^{(1)}}$ is a transfer function for the encoder, $W^{(1)} \in ℝ^{D^{(1)} \times D_{^{x}}}$ is a weight matrix, and $b^{(1)} \in ℝ^{D^{(1)}}$ is a bias vector. Then, the decoder maps the encoded representation z back into an estimate of the original input vector, x, as follows:

$\hat{x} = h^{^{(2)}} (W^{(2)} z + b^{(2)}),$

where the superscript (2) represents the second layer. $h^{(2)} : ℝ^{D_{x}} \to ℝ^{D_{x}}$ is the transfer function for the decoder, $W^{(1)} \in ℝ^{D_{^{x}} \times D^{(1)}}$ is a weight matrix, and $b^{(2)} \in ℝ^{D_{x}}$ is a bias vector.

Version History

Introduced in R2015b

decode

Syntax

Description

Input Arguments

autoenc — Trained autoencoder Autoencoder object

Z — Data encoded by autoenc matrix

Output Arguments

Y — Decoded data matrix | cell array of image data

Examples

Decode Encoded Data For New Images

Algorithms

Version History

See Also

`autoenc` — Trained autoencoder
`Autoencoder` object

`Z` — Data encoded by `autoenc`
matrix

`Y` — Decoded data
matrix | cell array of image data