How to estimate sensitivites of a neural net model with exogenous variables?

Is there a way to estimate the slope (first derivative) of the response function of a neural net model with respect to various inputs around a point? The measure I am looking for is similar to the beta coefficients in a linear regression.

Answer 1

[Greg Heath]

Differentiate the corresponding equation. For example, differentiate w.r.t. x:

 y = b2 + LW * tansig( b1 + IW * x )

Answer 2

[Anoush]

Thank you Greg. Is there an easy way of accessing the arrays of the model (b1,b2,LW,IW)? I am researching this myself, but if there is an obvious way please let me know.