Sum squared error performance function


perf = sse(net,t,y,ew)
[...] = sse(...,'regularization',regularization)
[...] = sse(...,'normalization',normalization)
[...] = sse(...,'squaredWeighting',squaredWeighting)
[...] = sse(...,FP)


sse is a network performance function. It measures performance according to the sum of squared errors.

perf = sse(net,t,y,ew) takes these input arguments and optional function parameters,


Neural network


Matrix or cell array of target vectors


Matrix or cell array of output vectors


Error weights (default = {1})

and returns the sum squared error.

This function has three optional function parameters which can be defined with parameter name/pair arguments, or as a structure FP argument with fields having the parameter name and assigned the parameter values.

[...] = sse(...,'regularization',regularization)

[...] = sse(...,'normalization',normalization)

[...] = sse(...,'squaredWeighting',squaredWeighting)

[...] = sse(...,FP)

  • regularization — can be set to any value between the default of 0 and 1. The greater the regularization value, the more squared weights and biases are taken into account in the performance calculation.

  • normalization — can be set to the default 'absolute', or 'normalized' (which normalizes errors to the [+2 -2] range consistent with normalized output and target ranges of [-1 1]) or 'percent' (which normalizes errors to the range [-1 +1]).

  • squaredWeighting — can be set to the default true, for applying error weights to squared errors; or false for applying error weights to the absolute errors before squaring.


Here a network is trained to fit a simple data set and its performance calculated

[x,t] = simplefit_dataset;
net = fitnet(10);
net.performFcn = 'sse';
net = train(net,x,t)
y = net(x)
e = t-y
perf = sse(net,t,y)

Network Use

To prepare a custom network to be trained with sse, set net.performFcn to 'sse'. This automatically sets net.performParam to the default function parameters.

Then calling train, adapt or perform will result in sse being used to calculate performance.

Was this topic helpful?