deep.transform.invlogit

Inverse logit transform

Since R2026a

collapse all in page

    Syntax

    Y = deep.transform.invlogit(X)

    Description

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

    example

    Examples

    collapse all

    Open Live Script

    Apply the inverse logit transform to random data.

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

    1.4810    2.3556   -0.9519    3.3135    3.1067
    2.2633    0.5424    0.1881   -1.6761   -0.0585
   -1.9279   -2.2249    3.1150    3.4967    1.3880

    Create a function layer that applies the inverse logit transform.

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

             Name: ''
       PredictFcn: @deep.transform.invlogit
      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

    collapse all

    Version History

    Introduced in R2026a

    See Also

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

    Topics