What is the difference between shap kernel-explainer and deep-explainer
I want to use shap to explain my image classification model.
I read that it is better to use shap.DeepExplainer
(than shap.KernelExplainer
) when using deep-learning models.
- What makes
DeepExplainer
works better in deep models thanKernelExplainer
? - What are the benefits of using
DeepExplainer
and notKernelExplainer
?
Topic shap explainable-ai deep-learning
Category Data Science