deep.transform.symmetric

Symmetric transform

Since R2026a

collapse all in page

    Syntax

    Y = deep.transform.symmetric(X)

    Description

    Y = deep.transform.symmetric(X) applies the symmetric transform to the input X. When you convert a Statistics and Machine Learning Toolbox™ neural network model that uses a symmetric score transform to a dlnetwork object, the last layer of the network is a function layer that applies the deep.transform.symmetric function.

    example

    Examples

    collapse all

    Open Live Script

    Apply the symmetric transform to random data.

    X = rand(3,5);
X = dlarray(X,"CB");
Y = deep.transform.symmetric(X)
    Y = 
  3(C) × 5(B) dlarray

    0.6294    0.8268   -0.4430    0.9298    0.9143
    0.8116    0.2647    0.0938   -0.6848   -0.0292
   -0.7460   -0.8049    0.9150    0.9412    0.6006

    Create a function layer that applies the symmetric transform.

    layer = functionLayer(@deep.transform.symmetric)
    layer = 
  FunctionLayer with properties:

             Name: ''
       PredictFcn: @deep.transform.symmetric
      Formattable: 0
    Acceleratable: 0

   Learnable Parameters
    No properties.

   State Parameters
    No properties.

  Show all properties

    Input Arguments

    collapse all

    Input data, specified as a dlarray object. X must have at most two dimensions.

    Output Arguments

    collapse all

    Transformed data, returned as a dlarray object that is the same size as X.

    Algorithms

    The symmetric transform is given by Y=2X−1.

    Version History

    Introduced in R2026a

    See Also

    | | | | | | | | | (Statistics and Machine Learning Toolbox) | (Statistics and Machine Learning Toolbox)

    Topics