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

1 回表示 (過去 30 日間)
Anoush
Anoush 2014 年 7 月 10 日
回答済み: Anoush 2014 年 7 月 13 日
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.

サインインしてこの質問に回答する。

採用された回答

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

その他の回答 (1 件)

Anoush
Anoush 2014 年 7 月 13 日
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.

カテゴリ

Help Center および File Exchange で Deep Learning Toolbox についてさらに検索

タグ

製品

Community Treasure Hunt

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

Start Hunting!

Translated by