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

1 vue (au cours des 30 derniers jours)
Anoush
Anoush le 10 Juil 2014
Réponse apportée : Anoush le 13 Juil 2014
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.

Connectez-vous pour répondre à cette question.

Réponse acceptée

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

Plus de réponses (1)

Anoush
Anoush le 13 Juil 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.

Catégories

En savoir plus sur Deep Learning Toolbox dans Help Center et File Exchange

Tags

Produits

Community Treasure Hunt

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

Start Hunting!

Translated by