Main Content

regressionLayer

(Not recommended) Regression output layer

collapse all in page

regressionLayer is not recommended. Use the trainnet function and set the loss function to "mse" instead. For more information, see Version History.

Syntax

layer = regressionLayer
layer = regressionLayer(Name,Value)

Description

A regression layer computes the half-mean-squared-error loss for regression tasks.

layer = regressionLayer returns a regression output layer for a neural network as a RegressionOutputLayer object.

layer = regressionLayer(Name,Value) sets the optional Name and ResponseNames properties using name-value pairs. For example, regressionLayer('Name','output') creates a regression layer with the name 'output'. Enclose each property name in single quotes.

example

Examples

collapse all

Create a regression output layer.

Create a regression output layer with the name 'routput'.

layer = regressionLayer('Name','routput')
layer = 
  RegressionOutputLayer with properties:

             Name: 'routput'
    ResponseNames: {}

   Hyperparameters
     LossFunction: 'mean-squared-error'

The default loss function for regression is mean-squared-error.

Include a regression output layer in a Layer array.

layers = [ ...
    imageInputLayer([28 28 1])
    convolution2dLayer(12,25)
    reluLayer
    fullyConnectedLayer(1)
    regressionLayer]
layers = 
  5x1 Layer array with layers:

     1   ''   Image Input         28x28x1 images with 'zerocenter' normalization
     2   ''   2-D Convolution     25 12x12 convolutions with stride [1  1] and padding [0  0  0  0]
     3   ''   ReLU                ReLU
     4   ''   Fully Connected     1 fully connected layer
     5   ''   Regression Output   mean-squared-error

Input Arguments

collapse all

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example: regressionLayer('Name','output') creates a regression layer with the name 'output'

Layer name, specified as a character vector or a string scalar. For Layer array input, the trainNetwork function automatically assigns names to layers with the name "".

The RegressionOutputLayer object stores this property as a character vector.

Data Types: char | string

Names of the responses, specified a cell array of character vectors or a string array. At training time, the software automatically sets the response names according to the training data. The default is {}.

Data Types: cell

Output Arguments

collapse all

Regression output layer, returned as a RegressionOutputLayer object.

More About

collapse all

Regression Output Layer

A regression layer computes the half-mean-squared-error loss for regression tasks. For typical regression problems, a regression layer must follow the final fully connected layer.

For a single observation, the mean-squared-error is given by:

MSE=∑i=1R(ti−yi)2R,

where R is the number of responses, ti is the target output, and yi is the network’s prediction for response i.

For image and sequence-to-one regression networks, the loss function of the regression layer is the half-mean-squared-error of the predicted responses, not normalized by R:

loss=12∑i=1R(ti−yi)2.

For image-to-image regression networks, the loss function of the regression layer is the half-mean-squared-error of the predicted responses for each pixel, not normalized by R:

loss=12∑p=1HWC(tp−yp)2,

where H, W, and C denote the height, width, and number of channels of the output respectively, and p indexes into each element (pixel) of t and y linearly.

For sequence-to-sequence regression networks, the loss function of the regression layer is the half-mean-squared-error of the predicted responses for each time step, not normalized by R:

loss=12S∑i=1S∑j=1R(tij−yij)2,

where S is the sequence length.

When training, the software calculates the mean loss over the observations in the mini-batch.

Extended Capabilities

Version History

Introduced in R2017a

collapse all

R2024a: Not recommended

Starting in R2024a, RegressionOutputLayer objects are not recommended, use the trainnet and set the loss function to "mse" instead.

There are no plans to remove support for RegressionOutputLayer objects. However, the trainnet function has these advantages and is recommended instead:

  • trainnet supports dlnetwork objects, which support a wider range of network architectures that you can create or import from external platforms.

  • trainnet enables you to easily specify loss functions. You can select from built-in loss functions or specify a custom loss function.

  • trainnet outputs a dlnetwork object, which is a unified data type that supports network building, prediction, built-in training, visualization, compression, verification, and custom training loops.

  • trainnet is typically faster than trainNetwork.

This table shows some typical usages of the trainNetwork function with RegressionOutputLayer objects and how to update your code to use the trainnet function instead.

Not RecommendedRecommended
net = trainNetwork(X,T,layers,options), where layers contains a RegressionOutputLayer object.

net = trainnet(X,T,layers,"mse",options);
In this example, layers specifies same network without a RegressionOutputLayer object.

net = trainNetwork(data,layers,options), where layers contains a RegressionOutputLayer object.

net = trainnet(data,layers,"mse",options);
In this example, layers specifies same network without a RegressionOutputLayer object.

See Also

| | |

Topics