Mean squared normalized error performance function
perf = mse(net,t,y,ew)
mse is a network performance function. It measures the network's performance according to the mean of squared errors.
perf = mse(net,t,y,ew) takes these arguments:
Matrix or cell array of targets
Matrix or cell array of outputs
Error weights (optional)
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.
Here a two-layer feedforward network is created and trained to predict median house prices using the mse performance function and a regularization value of 0.01, which is the default performance function for feedforwardnet.
[x,t] = house_dataset; net = feedforwardnet(10); net.performFcn = 'mse'; % Redundant, MSE is default net.performParam.regularization = 0.01; net = train(net,x,t); y = net(x); perf = perform(net,t,y);
Alternately, you can call this function directly.
perf = mse(net,x,t,'regularization',0.01);