mse

(To be removed) Mean squared normalized error performance function

mse 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.

Syntax

perf = mse(net,t,y,ew)

Description

Tip

To use mean squared error with deep learning, use the trainnet and set the loss function to "mse", or use the l2loss function for dlarray objects.

perf = mse(net,t,y,ew) takes a neural network, net, a matrix or cell array of targets, t, a matrix or cell array of outputs, y, and error weights, ew, and returns the mean squared error.

This function has two optional parameters, which are associated with networks whose net.trainFcn is set to this function:

• 'regularization' can be set to any value between 0 and 1. The greater the regularization value, the more squared weights and biases are included in the performance calculation relative to errors. The default is 0, corresponding to no regularization.

• 'normalization' can be set to 'none' (the default); 'standard', which normalizes errors between -2 and 2, corresponding to normalizing outputs and targets between -1 and 1; and 'percent', which normalizes errors between -1 and 1. This feature is useful for networks with multi-element outputs. It ensures that the relative accuracy of output elements with differing target value ranges are treated as equally important, instead of prioritizing the relative accuracy of the output element with the largest target value range.

You can create a standard network that uses mse with feedforwardnet or cascadeforwardnet. To prepare a custom network to be trained with mse, set net.performFcn to 'mse'. This automatically sets net.performParam to a structure with the default optional parameter values.

mse is a network performance function. It measures the network’s performance according to the mean of squared errors.

Examples

Train Neural Network Using mse Performance Function

This example shows how to train a neural network using the mse performance function.

Here a two-layer feedforward network is created and trained to estimate body fat percentage using the mse performance function and a regularization value of 0.01.

[x, t] = bodyfat_dataset;
net = feedforwardnet(10);
net.performParam.regularization = 0.01;

MSE is the default performance function for feedforwardnet.

net.performFcn

Train the network and evaluate performance.

net = train(net, x, t);
y = net(x);
perf = perform(net, t, y)

Alternatively, you can call mse directly.

perf = mse(net, t, y, 'regularization', 0.01)

Input Arguments

net — Neural network

network object

Neural network, specified as a network object.

Example: net = feedforwardnet(10);

t — Targets

matrix | cell array

Targets, specified as a matrix or a cell array.

y — Outputs

matrix | cell array

Outputs, specified as a matrix or a cell array.

ew — Error weights

1 (default) | scalar

Error weights, specified as a scalar.

Output Arguments

perf — Network performance

scalar

Performance of the network as the mean squared errors.

Version History

Introduced before R2006a

mse will be removed

mse will be removed in a future release.

To learn more about using metrics and loss functions when you train neural networks, see these examples and topics:

• Deep Learning Metrics

• Custom Loss Functions

• Monitor Deep Learning Training Progress

• ROC Curve and Performance Metrics

For dlnetwork objects, specify mean squared error (MSE) loss by setting the lossFcn of the trainnet function to "mse". For custom loss functions and custom training loops, use the l2loss function.

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