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

조회 수: 1 (최근 30일)
Anoush
Anoush 2014년 7월 10일
답변: Anoush 2014년 7월 13일
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.

이 질문에 답변하려면 로그인하십시오.

채택된 답변

Greg Heath
Greg Heath 2014년 7월 11일
Differentiate the corresponding equation. For example, differentiate w.r.t. x:
y = b2 + LW * tansig( b1 + IW * x )

추가 답변 (1개)

Anoush
Anoush 2014년 7월 13일
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.

카테고리

Help Center 및 File Exchange에서 Deep Learning Toolbox에 대해 자세히 알아보기

태그

제품

Community Treasure Hunt

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

Start Hunting!

Translated by