sse (Neural Network Toolbox)

Neural Network Toolbox

sse

Sum squared error performance function

Syntax

perf = sse(E,X,PP)

perf = sse(E,net,PP)

info = sse(code)

Description

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

sse(E,X,PP) takes from one to three arguments,

E -- Matrix or cell array of error vector(s)

X -- Vector of all weight and bias values (ignored)

PP -- Performance parameters (ignored)

and returns the sum squared error.

sse(E,net,PP) can take an alternate argument to X,

net -- Neural network from which X can be obtained (ignored)

sse(code) returns useful information for each code string:

'deriv' -- Name of derivative function

'name' -- Full name

'pnames' -- Names of training parameters

'pdefaults' -- Default training parameters

Examples

Here a two-layer feed-forward is created with a 1-element input ranging from -10 to 10, four hidden tansig neurons, and one purelin output neuron.

net = newff([-10 10],[4 1],{'tansig','purelin'});

Here the network is given a batch of inputs P. The error is calculated by subtracting the output A from target T. Then the sum squared error is calculated.

p = [-10 -5 0 5 10];
t = [0 0 1 1 1];
y = sim(net,p)
e = t-y
perf = sse(e)

Note that sse can be called with only one argument because the other arguments are ignored. sse supports those arguments to conform to the standard performance function argument list.

Network Use

To prepare a custom network to be trained with sse, set net.performFcn to 'sse'. This will automatically set net.performParam to the empty matrix [], as sse has no performance parameters.

Calling train or adapt will result in sse being used to calculate performance.

See Also

dsse

srchhyb sumsqr