What is the output of the function 'staticderiv'?

Hello,

from the very sparse documentation of the function 'staticderiv' I could extract that apparently it delivers the derivative of the cost function with respect to the weights and biases of a neural network (such as created by 'feedforwardnet'). However, the output of the function 'staticderiv' ist just a vector with dimensions equal to the number of parameters in the network.

It is unclear to me what entry in the vector corresponds to the derivative w.r.t to which parameter.

Can someone clarify this?

[Fabricio Braga]

I'm having the same problem as you. It is difficult to identify the relationship that each element of this single response vector has with weights and bias.

Did you come up with any ideas?