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

1 visualización (últimos 30 días)
Anoush
Anoush el 10 de Jul. de 2014
Respondida: Anoush el 13 de Jul. de 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.

Iniciar sesión para responder a esta pregunta.

Respuesta aceptada

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

Más respuestas (1)

Anoush
Anoush el 13 de Jul. de 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.

Categorías

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Etiquetas

Productos

Community Treasure Hunt

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

Start Hunting!

Translated by