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

1 view (last 30 days)
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.

Accepted Answer

Greg Heath
Greg Heath on 11 Jul 2014
Differentiate the corresponding equation. For example, differentiate w.r.t. x:
y = b2 + LW * tansig( b1 + IW * x )

More Answers (1)

Anoush
Anoush on 13 Jul 2014
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.

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!