资源分类
》 资源 》算法》explaining-black-boxes

explaining-black-boxes

2020-02-14 | |  44 |   0 |   0

Explaining black boxes

Using SHAP (SHapely Additive exPlanation)

Random Forest

  • Overall weight

  • 图片.png

Shap values of all the records representing which variable play what kind of role in predicting the output. Eg: Sex when High (Male) playe a negative role in survival but female have very high chances of survival spread across other factors too

图片.png

图片.png

图片.png

Using eli5 (Explain like I'm 5)

Logistic Regression

  • Overall weight

图片.png

图片.png

上一篇：tds_black_box_models_more_explainable

下一篇：tensorflow-value-iteration-networks

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...